mirror of
https://github.com/Ark0N/Codeman.git
synced 2026-11-14 10:39:32 +01:00
feat(local-model): list every model that fits, and add Muse Glimmer 30B
The "Run a local model" chooser showed the pick and four more models. It now lists every catalogue model that fits the Mac, and the install accepts every listed row. - MAX_ALTERNATIVES goes from 4 to 11, above what the catalogue holds. It stays a bound: test/local-model-catalog.test.ts fails for a catalogue that outgrows it, so nothing drops off the list unseen. - New row `muse-glimmer:30b-q4_k_m` (Meta, Apache-2.0): SWE-bench Verified 76.0, SWE-bench Pro 51.2, Terminal-Bench 2.1 51.7 on Meta's card. Its K/V cache is the smallest of the 27B class, so it is the first model of that class a 32 GB Mac holds: 21.2 GB at 65,536 tokens, 0.970 of the estimated budget. Figures computed from its config.json and its GGUF header by the llamacpp rule (13 full-attention layers, 39 sliding-window layers of 2,048 tokens, no prediction layer); the sliding-window cache rule was read again in llama.cpp b12111 (src/llama-kv-cache-iswa.cpp). Never run on a Mac: `estimated`. - What changes for a Mac: 32 GB is no longer `limited`. On an M1 Max or M2 Max the pick is Muse Glimmer; on a base or Pro chip the dense model is slow and the pick stays MiMo V2.6 9B, now with the small-pick note. Every other pick is unchanged. - The "set aside" list was read again at its sources on 2026-11-10 and gained ripple-preview:65b (every build requires runtime 0.40.16, one above the pin), Ornith 1.0 (runtime issue 16992), nemotron-3.5-super:120b, qwen3.5:4b, qwen3-coder-next and the MLX and DFlash tags of Muse Glimmer. - The header and the guide now say that runtime issue 16992 has one diagnosed cause in the tool parser every Qwen-family row shares (a tool argument that quotes a whole tool call is cut off; the fix is runtime PR 17021, open). Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer committed
1 parent
f62c1f7e2f
commit
9608a17d99
9 files changed
+271
-88
No files matched your search
@@ -31,6 +31,7 @@ import {
|
||||
LocalModelCatalogSchema,
|
||||
STOCK_LOCAL_MODEL_CATALOG,
|
||||
} from '../src/config/local-model-catalog.js';
|
||||
import { MAX_ALTERNATIVES } from '../src/local-model/recommend.js';
|
||||
import {
|
||||
RUNTIME_CTX_CHECKPOINTS,
|
||||
RUNTIME_HOST_PROMPT_CACHE_MIB,
|
||||
@@ -63,9 +64,10 @@ const GIB = 1024 * MIB;
|
||||
|
||||
/**
|
||||
* The architecture of every model the stock catalogue lists, read from its config.json on
|
||||
* Hugging Face (2026-11-08): full-attention layers, their K/V heads and head size, and the
|
||||
* layers whose cache does not grow with the context (Gated DeltaNet layers with their value
|
||||
* and key heads, or sliding-window layers with their window). Fine-tunes share their base's.
|
||||
* Hugging Face (2026-11-08; Muse Glimmer on 2026-11-10): full-attention layers, their K/V heads
|
||||
* and head size, and the layers whose cache does not grow with the context (Gated DeltaNet
|
||||
* layers with their value and key heads, or sliding-window layers with their window).
|
||||
* Fine-tunes share their base's.
|
||||
*/
|
||||
const ARCHITECTURES = {
|
||||
'Qwen3.5-9B': { attentionLayers: 8, kvHeads: 4, headDim: 256, linear: { layers: 24, vHeads: 32, kHeads: 16 } },
|
||||
@@ -78,6 +80,8 @@ const ARCHITECTURES = {
|
||||
linear: { layers: 36, vHeads: 64, kHeads: 16 },
|
||||
},
|
||||
'North-Mini-Code-1.0': { attentionLayers: 13, kvHeads: 4, headDim: 128, sliding: { layers: 36, window: 4096 } },
|
||||
// 52 layers, three in four on a sliding window (the GGUF header's `sliding_window_pattern`).
|
||||
'Muse-Glimmer-30B': { attentionLayers: 13, kvHeads: 2, headDim: 128, sliding: { layers: 39, window: 2048 } },
|
||||
} as const;
|
||||
|
||||
type ArchitectureName = keyof typeof ARCHITECTURES;
|
||||
@@ -86,7 +90,8 @@ type Architecture = (typeof ARCHITECTURES)[ArchitectureName];
|
||||
/**
|
||||
* Which architecture each stock row runs, and how many tokens the runtime drafts per step with
|
||||
* its multi-token-prediction layer: 0 when the GGUF has none (`nextn_predict_layers` in the GGUF
|
||||
* header, read on 2026-11-08 from the first bytes of each model layer), else the tag's own
|
||||
* header, read on 2026-11-08 from the first bytes of each model layer; on 2026-11-10 for the
|
||||
* Muse Glimmer row), else the tag's own
|
||||
* `draft_num_predict` (its params layer) or the runtime's default of 4 when the tag sets none.
|
||||
* Prediction costs a cache for that layer and one rollback copy of the recurrent state per
|
||||
* drafted token (see the catalogue header). A row the catalogue gains must be added here, or the
|
||||
@@ -96,6 +101,8 @@ const ROW_ARCHITECTURE: Record<string, { architecture: ArchitectureName; draftTo
|
||||
'qwen3.5:9b-q4_k_m': { architecture: 'Qwen3.5-9B', draftTokens: 0 },
|
||||
'mimo-v2.6:9b-q4_k_m': { architecture: 'Qwen3.5-9B', draftTokens: 0 },
|
||||
'north-mini-code-1.0:q4_k_m': { architecture: 'North-Mini-Code-1.0', draftTokens: 0 },
|
||||
// No prediction layer; the tags with a separate draft model (`-dflash`) are not listed.
|
||||
'muse-glimmer:30b-q4_k_m': { architecture: 'Muse-Glimmer-30B', draftTokens: 0 },
|
||||
// Its params layer sets `draft_num_predict` 2.
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m': { architecture: 'Qwen3.6-35B-A3B', draftTokens: 2 },
|
||||
'qwen3.6:35b-a3b': { architecture: 'Qwen3.6-35B-A3B', draftTokens: 0 },
|
||||
@@ -183,20 +190,21 @@ describe('the stock catalogue', () => {
|
||||
expect(getLocalModelCatalog()).toBe(first);
|
||||
});
|
||||
|
||||
it('lists eight models, by rank, and none of those set aside in the header', () => {
|
||||
it('lists nine models, by rank, and none of those set aside in the header', () => {
|
||||
expect(models.map((m) => m.id)).toEqual([
|
||||
'qwen3.5:9b-q4_k_m',
|
||||
'mimo-v2.6:9b-q4_k_m',
|
||||
'north-mini-code-1.0:q4_k_m',
|
||||
'muse-glimmer:30b-q4_k_m',
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m',
|
||||
'qwen3.6:35b-a3b',
|
||||
'qwen3.8:27b-q8_0',
|
||||
'qwen3.8:27b-mtp-q4_k_m',
|
||||
'ornith-1.5:122b',
|
||||
]);
|
||||
expect(models.map((m) => m.rank)).toEqual([1, 2, 3, 4, 5, 6, 7, 8]);
|
||||
expect(models.map((m) => m.rank)).toEqual([1, 2, 3, 4, 5, 6, 7, 8, 9]);
|
||||
const setAside =
|
||||
/^(bonsai-2|gpt-oss|flint|lfm2\.5|laguna|qwen3\.8-flash-next|qwen3\.5:122b)|^ornith-1\.5:(9b|35b|397b)/;
|
||||
/^(bonsai-2|gpt-oss|flint|lfm2\.5|laguna|qwen3\.8-flash-next|qwen3\.5:(122b|4b)|ripple-preview|nemotron-3\.5-super|qwen3-coder-next)|^ornith-1\.5:(9b|35b|397b)|^ornith:(9b|35b)|^muse-glimmer:.*(mlx|dflash)/;
|
||||
expect(models.filter((m) => setAside.test(m.id)).map((m) => m.id)).toEqual([]);
|
||||
// The plain 9B and 27B tags are MLX builds on a Mac: their GGUF builds are listed instead.
|
||||
for (const plain of ['qwen3.5:9b', 'mimo-v2.6:9b', 'qwen3.8:27b']) {
|
||||
@@ -209,6 +217,7 @@ describe('the stock catalogue', () => {
|
||||
'qwen3.5:9b-q4_k_m': 'llamacpp',
|
||||
'mimo-v2.6:9b-q4_k_m': 'llamacpp',
|
||||
'north-mini-code-1.0:q4_k_m': 'llamacpp',
|
||||
'muse-glimmer:30b-q4_k_m': 'llamacpp',
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m': 'llamacpp',
|
||||
// Manifest lists: a Mac takes the MLX child.
|
||||
'qwen3.6:35b-a3b': 'mlx',
|
||||
@@ -224,6 +233,8 @@ describe('the stock catalogue', () => {
|
||||
'qwen3.5:9b-q4_k_m': 6_550_825_550,
|
||||
'mimo-v2.6:9b-q4_k_m': 6_550_811_033,
|
||||
'north-mini-code-1.0:q4_k_m': 18_593_967_008,
|
||||
// Fetched on 2026-11-10: 16.76 GB of weights and a 1.40 GB projector.
|
||||
'muse-glimmer:30b-q4_k_m': 18_157_010_252,
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m': 22_621_314_381,
|
||||
// The MLX child of the list, and the total of a real pull on a Mac, byte for byte.
|
||||
'qwen3.6:35b-a3b': 23_105_798_956,
|
||||
@@ -256,6 +267,8 @@ describe('the stock catalogue', () => {
|
||||
'qwen3.5:9b-q4_k_m': [9, 'Apache-2.0'],
|
||||
'mimo-v2.6:9b-q4_k_m': [9, 'MIT'],
|
||||
'north-mini-code-1.0:q4_k_m': [30, 'Apache-2.0'],
|
||||
// The card's total: a 27.9B language model and a vision encoder.
|
||||
'muse-glimmer:30b-q4_k_m': [29.6, 'Apache-2.0'],
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m': [35, 'Apache-2.0'],
|
||||
'qwen3.6:35b-a3b': [35, 'Apache-2.0'],
|
||||
'qwen3.8:27b-q8_0': [27.8, 'Apache-2.0'],
|
||||
@@ -281,6 +294,8 @@ describe('the stock catalogue', () => {
|
||||
'mimo-v2.6:9b-q4_k_m': 9.3,
|
||||
// The 35B-A3B's llama.cpp figure: both have 3 billion active parameters.
|
||||
'north-mini-code-1.0:q4_k_m': 13.6,
|
||||
// The dense 27B's figure: the weights of the two are the same size.
|
||||
'muse-glimmer:30b-q4_k_m': 2.95,
|
||||
// 54.5 on 400 GB/s with llama.cpp.
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m': 13.6,
|
||||
// 67.8 on 400 GB/s with MLX.
|
||||
@@ -302,6 +317,13 @@ describe('the stock catalogue', () => {
|
||||
]);
|
||||
});
|
||||
|
||||
it('holds no more models than one window lists: the pick and MAX_ALTERNATIVES others', () => {
|
||||
// recommend() cuts the list at MAX_ALTERNATIVES. While the catalogue stays under it, a Mac
|
||||
// is shown every model that fits and the install accepts every one of them. A catalogue
|
||||
// that outgrows the bound must fail here, so the bound is raised (or kept) on purpose.
|
||||
expect(models.length - 1).toBeLessThanOrEqual(MAX_ALTERNATIVES);
|
||||
});
|
||||
|
||||
it('names the oldest macOS and its schema version', () => {
|
||||
expect(STOCK_LOCAL_MODEL_CATALOG.minMacosMajor).toBe(14);
|
||||
expect(STOCK_LOCAL_MODEL_CATALOG.schema).toBe(1);
|
||||
@@ -351,6 +373,8 @@ describe('the memory figures of the stock rows: each row has its own', () => {
|
||||
'mimo-v2.6:9b-q4_k_m': [17_408, 2_547_960_320, 0],
|
||||
// The sliding window x (1 live + 8 checkpoints) + 1.0 GB + 1 GiB.
|
||||
'north-mini-code-1.0:q4_k_m': [14_144, 3_698_117_120, 0],
|
||||
// The same rule: 39 layers x 2,560 cells x 544 bytes = 54,312,960 per copy.
|
||||
'muse-glimmer:30b-q4_k_m': [7_072, 2_562_558_464, 0],
|
||||
// State x (1 live + 2 rollback copies + 8 checkpoints) + 1.0 GB + 1 GiB; the prediction
|
||||
// layer's cache in f16 per token. The 27B rows below draft 4 tokens: 4 rollback copies.
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m': [12_928, 2_798_242_304, 0],
|
||||
|
||||
@@ -12,9 +12,9 @@
|
||||
*/
|
||||
|
||||
import { describe, expect, it } from 'vitest';
|
||||
import { getLocalModelCatalog } from '../src/config/local-model-catalog.js';
|
||||
import { getLocalModelCatalog, LocalModelCatalogSchema } from '../src/config/local-model-catalog.js';
|
||||
import { formatGb, memClassGb } from '../src/local-model/format.js';
|
||||
import { modelFitsBudget, recommend } from '../src/local-model/recommend.js';
|
||||
import { MAX_ALTERNATIVES, modelFitsBudget, recommend } from '../src/local-model/recommend.js';
|
||||
import type { HardwareFacts, HarnessFact } from '../src/types.js';
|
||||
|
||||
/** A Mac with Apple silicon and `gb` GB of memory as sold. */
|
||||
@@ -72,18 +72,46 @@ describe('modelFitsBudget', () => {
|
||||
}
|
||||
});
|
||||
|
||||
it('does not depend on the ranking: a model that fits and is listed nowhere still fits', () => {
|
||||
// On a 128 GB Mac more models fit than the recommendation lists.
|
||||
const hw = mac(128, 'Apple M5 Max');
|
||||
it('does not depend on what the recommendation lists: a model left out for disk space still fits', () => {
|
||||
// The recommendation lists every model that fits the memory, unless its download would
|
||||
// leave under 10 GiB on the disk. With 40 GB free on a 128 GB Mac that leaves out the two
|
||||
// largest downloads, which fit the memory all the same.
|
||||
const hw = { ...mac(128, 'Apple M5 Max'), freeDiskBytes: 40_000_000_000 };
|
||||
const offered = recommend(hw, catalog, harnessFacts());
|
||||
const listed = new Set([offered.pick, ...offered.alternatives].map((row) => row?.modelId));
|
||||
const unlisted = catalog.models.filter((model) => !listed.has(model.id));
|
||||
expect(unlisted.length).toBeGreaterThan(0);
|
||||
expect(unlisted.map((model) => model.id)).toEqual(['qwen3.8:27b-q8_0', 'ornith-1.5:122b']);
|
||||
for (const model of unlisted) {
|
||||
expect(modelFitsBudget(hw, catalog, model.id, model.contexts.at(-1) as number), model.id).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('does not depend on the ranking: a model cut off by the length of the list still fits', () => {
|
||||
// A catalogue longer than the list: the stock rows plus six more copies of its smallest.
|
||||
const smallest = catalog.models[0];
|
||||
const long = LocalModelCatalogSchema.parse({
|
||||
...structuredClone(catalog),
|
||||
models: [
|
||||
...structuredClone(catalog.models),
|
||||
...Array.from({ length: 6 }, (_, index) => ({
|
||||
...structuredClone(smallest),
|
||||
id: `extra-${index + 1}:9b`,
|
||||
rank: -1 - index,
|
||||
})),
|
||||
],
|
||||
});
|
||||
expect(long.models.length).toBeGreaterThan(1 + MAX_ALTERNATIVES);
|
||||
const hw = mac(512, 'Apple M5 Max');
|
||||
const offered = recommend(hw, long, harnessFacts());
|
||||
const listed = new Set([offered.pick, ...offered.alternatives].map((row) => row?.modelId));
|
||||
expect(listed.size).toBe(1 + MAX_ALTERNATIVES);
|
||||
const unlisted = long.models.filter((model) => !listed.has(model.id));
|
||||
expect(unlisted.length).toBe(long.models.length - 1 - MAX_ALTERNATIVES);
|
||||
for (const model of unlisted) {
|
||||
expect(modelFitsBudget(hw, long, model.id, model.contexts.at(-1) as number), model.id).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('rules out a model that is too large, and one the catalogue does not have', () => {
|
||||
expect(modelFitsBudget(mac(48), catalog, 'ornith-1.5:122b', 131072)).toBe(false);
|
||||
expect(modelFitsBudget(mac(48), catalog, 'no-such:1b', 65536)).toBe(false);
|
||||
|
||||
@@ -489,6 +489,8 @@ describe('needBytes', () => {
|
||||
'qwen3.5:9b-q4_k_m': 11_380_487_246,
|
||||
'mimo-v2.6:9b-q4_k_m': 11_380_472_729,
|
||||
'north-mini-code-1.0:q4_k_m': 25_999_848_864,
|
||||
// At its own window of 131072 tokens: 18.2 GB + 0.9 GB of K/V cache + 2.6 GB.
|
||||
'muse-glimmer:30b-q4_k_m': 21_646_509_900,
|
||||
'qwen3.6:35b-a3b-mtp-q4_k_m': 28_808_554_317,
|
||||
'qwen3.6:35b-a3b': 35_955_462_956,
|
||||
'qwen3.8:27b-q8_0': 44_292_142_594,
|
||||
@@ -544,6 +546,9 @@ describe('the fit grade', () => {
|
||||
// ---------- 2. The two real Macs ----------
|
||||
|
||||
describe('the MacBook Pro (Mac17,13: Apple M5 Pro, 48 GB)', () => {
|
||||
/** The same Mac without the probe: 48 GiB and the chip are all the fit and the speed depend on. */
|
||||
const hw48 = mac(48, 'Apple M5 Pro');
|
||||
|
||||
/**
|
||||
* Expected: Qwen3.6 35B-A3B at 131,072 tokens with OpenCode, a TIGHT fit, 67.7 tokens per
|
||||
* second, "Recommended for this Mac".
|
||||
@@ -642,7 +647,7 @@ describe('the MacBook Pro (Mac17,13: Apple M5 Pro, 48 GB)', () => {
|
||||
expect(result.notes).toEqual([]);
|
||||
});
|
||||
|
||||
it('lists four other models that fit, each at the largest context it fits at, the fast ones first', async () => {
|
||||
it('lists every other model that fits, each at the largest context it fits at, the fast ones first', async () => {
|
||||
const result = recommend(await macbook(), STOCK, ALL_INSTALLED);
|
||||
expect(
|
||||
result.alternatives.map((c) => [c.modelId, c.context, c.fit, c.speed, c.tokensPerSecond ?? null, c.tag?.kind])
|
||||
@@ -652,15 +657,19 @@ describe('the MacBook Pro (Mac17,13: Apple M5 Pro, 48 GB)', () => {
|
||||
['north-mini-code-1.0:q4_k_m', 262144, 'good', 'ok', 41.8, undefined],
|
||||
['mimo-v2.6:9b-q4_k_m', 131072, 'good', 'ok', 28.6, 'small'],
|
||||
['qwen3.5:9b-q4_k_m', 131072, 'good', 'ok', 28.6, 'small'],
|
||||
// The dense models compute to 2.95 x 3.07 = 9.1 tokens per second on this chip (5.2 in
|
||||
// 8 bits): slow, so they come after every fast model, in the order of their rank.
|
||||
['qwen3.8:27b-mtp-q4_k_m', 262144, 'tight', 'slow', 9.1, 'tight'],
|
||||
['qwen3.8:27b-q8_0', 65536, 'tight', 'slow', 5.2, 'tight'],
|
||||
['muse-glimmer:30b-q4_k_m', 131072, 'good', 'slow', 9.1, 'slow'],
|
||||
]);
|
||||
// Only the tested row rests on a measurement of that model.
|
||||
expect(result.alternatives.map((c) => c.needSource)).toEqual(['estimated', 'estimated', 'estimated', 'estimated']);
|
||||
// The dense 27B fits too (32.1 GB at 262144) but computes to 2.95 x 3.07 = 9.1 tokens per
|
||||
// second here: slow, so it ranks after four fast models and is not listed.
|
||||
expect(modelFitsBudget(await macbook(), STOCK, 'qwen3.8:27b-mtp-q4_k_m', 262144)).toBe(true);
|
||||
expect(order(result).some((entry) => entry.startsWith('qwen3.8:27b'))).toBe(false);
|
||||
expect(new Set(result.alternatives.map((c) => c.needSource))).toEqual(new Set(['estimated']));
|
||||
// Every model of the catalogue that fits is on the list: nothing is cut off after four.
|
||||
const fitting = STOCK.models.filter((m) => m.contexts.some((ctx) => modelFitsBudget(hw48, STOCK, m.id, ctx)));
|
||||
expect(rows(result).map((c) => c.modelId).sort()).toEqual(fitting.map((m) => m.id).sort());
|
||||
// The 122B fits at no context.
|
||||
expect(order(result).some((entry) => entry.startsWith('ornith'))).toBe(false);
|
||||
expect(order(result).some((entry) => entry.startsWith('ornith-1.5'))).toBe(false);
|
||||
});
|
||||
|
||||
it('would get the same model as "Best fit", with the estimated speed, had nobody tested it', async () => {
|
||||
@@ -692,7 +701,10 @@ describe('the MacBook Pro (Mac17,13: Apple M5 Pro, 48 GB)', () => {
|
||||
['qwen3.8:27b-mtp-q4_k_m', 'unknown'],
|
||||
['qwen3.8:27b-q8_0', 'unknown'],
|
||||
['qwen3.6:35b-a3b-mtp-q4_k_m', 'unknown'],
|
||||
['muse-glimmer:30b-q4_k_m', 'unknown'],
|
||||
['north-mini-code-1.0:q4_k_m', 'unknown'],
|
||||
['mimo-v2.6:9b-q4_k_m', 'unknown'],
|
||||
['qwen3.5:9b-q4_k_m', 'unknown'],
|
||||
]);
|
||||
});
|
||||
});
|
||||
@@ -803,10 +815,13 @@ describe('every memory size, with the stock catalogue', () => {
|
||||
[24, 'Apple M3', 'limited mimo-v2.6:9b-q4_k_m@131072 good slow'],
|
||||
[24, 'Apple M4', 'limited mimo-v2.6:9b-q4_k_m@131072 good ok'],
|
||||
[24, 'Apple M4 Pro', 'limited mimo-v2.6:9b-q4_k_m@131072 good ok'],
|
||||
// North Mini Code needs 23.2 GB at 65536 tokens: 1.06 of the 21.8 GB estimate. A runtime
|
||||
// that measures about 3/4 of the memory admits it (see below).
|
||||
[32, 'Apple M4', 'limited mimo-v2.6:9b-q4_k_m@131072 good ok'],
|
||||
[32, 'Apple M1 Max', 'limited mimo-v2.6:9b-q4_k_m@131072 good ok'],
|
||||
// Muse Glimmer 30B fits at 65536 tokens: 21.2 GB, 0.970 of the 21.8 GB estimate. So a 32 GB
|
||||
// Mac is no small-model Mac (`ok`). The model is dense: on a base chip it computes to 3.5
|
||||
// tokens per second and the fast 9B stays the pick, on a Max chip (11.8) it is the pick.
|
||||
// North Mini Code needs 23.2 GB at 65536 tokens, 1.06 of the estimate: a runtime that
|
||||
// measures about 3/4 of the memory admits it (see below).
|
||||
[32, 'Apple M4', 'ok mimo-v2.6:9b-q4_k_m@131072 good ok'],
|
||||
[32, 'Apple M1 Max', 'ok muse-glimmer:30b-q4_k_m@65536 tight ok'],
|
||||
// A Max chip runs the dense 27B fast enough (12.1); an M3 Max (300 GB/s) does not (8.9),
|
||||
// and takes the 35B-A3B as a GGUF build, whose memory does not grow after it loaded. Both
|
||||
// at 131072 tokens, 0.966 and 0.971 of the budget.
|
||||
@@ -850,14 +865,21 @@ describe('every memory size, with the stock catalogue', () => {
|
||||
expect(smallest / result.budgetBytes).toBeGreaterThan(4);
|
||||
});
|
||||
|
||||
it('gives no model to 8 and 16 GB, a small model to every Mac from 18 to 32 GB, and every larger one a model of 27 billion or more', () => {
|
||||
it('gives no model to 8 and 16 GB, a small model to every Mac of 18 and 24 GB, and every Mac from 36 GB a model of 27 billion or more', () => {
|
||||
for (const hw of SWEEP) {
|
||||
const result = recommend(hw, STOCK, ALL_INSTALLED);
|
||||
const label = `${hw.memClassGb} GB ${hw.chip}`;
|
||||
if (hw.memClassGb <= 16) expect(result.reason, label).toBe('memory');
|
||||
else if (hw.memClassGb <= 32) {
|
||||
else if (hw.memClassGb <= 24) {
|
||||
expect(result.verdict, label).toBe('limited');
|
||||
expect(result.pick?.paramsB, label).toBe(9);
|
||||
} else if (hw.memClassGb === 32) {
|
||||
// A model of 30 billion fits, so the Mac is not `limited`. It is dense: the pick only
|
||||
// where it is not slow (a chip this file knows is fast, or one it knows nothing about).
|
||||
expect(result.verdict, label).toBe('ok');
|
||||
expect(rows(result).map((c) => c.modelId), label).toContain('muse-glimmer:30b-q4_k_m');
|
||||
expect(result.pick?.paramsB, label).toBe(hw.chip === 'Apple M4' ? 9 : 29.6);
|
||||
if (hw.chip === 'Apple M4') expect(result.notes[0], label).toEqual({ text: LOCAL_MODEL_LABELS.noteSmallPick });
|
||||
} else {
|
||||
expect(result.verdict, label).toBe('ok');
|
||||
expect(result.pick?.paramsB, label).toBeGreaterThanOrEqual(27);
|
||||
@@ -1620,11 +1642,13 @@ describe('the ranking', () => {
|
||||
expect(result.pick).toMatchObject({ context: 1024, fit: 'tight', budgetShare: 0.92 });
|
||||
});
|
||||
|
||||
it('lists each model once, never the pick again, and at most four alternatives', () => {
|
||||
expect(MAX_ALTERNATIVES).toBe(4);
|
||||
// Seven models fit a 128 GB Mac; the pick plus four are shown.
|
||||
it('lists each model once, never the pick again, and every model that fits', () => {
|
||||
// The bound is above what either catalogue holds, so nothing that fits is cut off.
|
||||
expect(MAX_ALTERNATIVES).toBe(11);
|
||||
for (const [, catalog] of BOTH) expect(catalog.models.length - 1).toBeLessThanOrEqual(MAX_ALTERNATIVES);
|
||||
// Seven models fit a 128 GB Mac: the pick and all six others are shown.
|
||||
const result = recommend(mac(128, 'Apple M5 Ultra'), RULES, ALL_INSTALLED);
|
||||
expect(result.alternatives).toHaveLength(4);
|
||||
expect(result.alternatives).toHaveLength(6);
|
||||
const ids = rows(result).map((c) => c.modelId);
|
||||
expect(new Set(ids).size).toBe(ids.length);
|
||||
for (const [, catalog] of BOTH) {
|
||||
@@ -1633,9 +1657,26 @@ describe('the ranking', () => {
|
||||
const sweptIds = rows(swept).map((c) => c.modelId);
|
||||
expect(new Set(sweptIds).size).toBe(sweptIds.length);
|
||||
expect(swept.alternatives.length).toBeLessThanOrEqual(MAX_ALTERNATIVES);
|
||||
// Every model that fits at a context a harness works at is on the list (the sweep's
|
||||
// Macs have 500 GB of free disk, so none is left out for room).
|
||||
const fitting = catalog.models.filter((m) =>
|
||||
m.contexts.some((ctx) => ctx >= 65536 && modelFitsBudget(hw, catalog, m.id, ctx))
|
||||
);
|
||||
expect([...sweptIds].sort(), `${hw.memClassGb} GB ${hw.chip}`).toEqual(fitting.map((m) => m.id).sort());
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
it('still cuts a list longer than the bound, and the install can only take what is listed', () => {
|
||||
// Fourteen models that all fit: the pick and MAX_ALTERNATIVES others, best rank first.
|
||||
const many = catalogOf(
|
||||
Array.from({ length: 14 }, (_, index) => modelNeeding(`m${index + 1}:x`, GIB, { rank: index + 1 }))
|
||||
);
|
||||
const result = recommend(HUNDRED_GIB_MAC, many, [fact('alpha')]);
|
||||
expect(rows(result)).toHaveLength(1 + MAX_ALTERNATIVES);
|
||||
expect(rows(result)[0].modelId).toBe('m14:x');
|
||||
expect(rows(result).at(-1)?.modelId).toBe('m3:x');
|
||||
});
|
||||
});
|
||||
|
||||
describe('harnesses', () => {
|
||||
@@ -2064,6 +2105,8 @@ describe('what each row of the chooser carries', () => {
|
||||
'qwen3.5:9b-q8_0': 'estimated',
|
||||
'qwen3.5:9b': 'estimated',
|
||||
'gpt-oss:20b': 'estimated',
|
||||
// Slow on this chip, so it was the sixth row: listed since the list holds every model.
|
||||
'qwen3.8:27b-q8_0': 'estimated',
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -2075,10 +2118,15 @@ describe('the measured budget, end to end', () => {
|
||||
const measured = recommend(hw, STOCK, ALL_INSTALLED, { measuredTotalBytes: MACBOOK_MEASURED_TOTAL });
|
||||
expect([estimated.budgetSource, estimated.budgetGb]).toEqual(['estimated', '37.6']);
|
||||
expect([measured.budgetSource, measured.budgetGb]).toEqual(['measured', '40.2']);
|
||||
// The same rows in the same order; only the share of each changes.
|
||||
expect(order(measured)).toEqual(order(estimated));
|
||||
expect(rows(estimated).map((c) => c.budgetShare)).toEqual([0.957, 0.767, 0.692, 0.303, 0.303]);
|
||||
expect(rows(measured).map((c) => c.budgetShare)).toEqual([0.895, 0.717, 0.647, 0.283, 0.283]);
|
||||
// The same models in the same order. The share of each changes, and one model steps up a
|
||||
// context: the 27B in 8 bits fits 65536 tokens under the estimate (0.975) and 131072 under
|
||||
// what the runtime reported (0.976).
|
||||
expect(rows(measured).map((c) => c.modelId)).toEqual(rows(estimated).map((c) => c.modelId));
|
||||
const stepped = order(estimated).filter((entry, index) => order(measured)[index] !== entry);
|
||||
expect(stepped).toEqual(['qwen3.8:27b-q8_0@65536']);
|
||||
expect(order(measured)).toContain('qwen3.8:27b-q8_0@131072');
|
||||
expect(rows(estimated).map((c) => c.budgetShare)).toEqual([0.957, 0.767, 0.692, 0.303, 0.303, 0.853, 0.975, 0.576]);
|
||||
expect(rows(measured).map((c) => c.budgetShare)).toEqual([0.895, 0.717, 0.647, 0.283, 0.283, 0.798, 0.976, 0.539]);
|
||||
for (const candidate of rows(measured)) {
|
||||
expect(candidate.budgetShare).toBeCloseTo(candidate.needBytes / MACBOOK_MEASURED_TOTAL, 3);
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user