Will It Run AI

MistralMistral

Mistral Small 4 119B

最先端
huggingfaceHuggingFace
52.6Kダウンロード380いいねJan 2026公開日256K トークンコンテキストMistral Research Licenseライセンス94 卓越品質

Mistral Small 4 119B (119B parameters) requires approximately 79.5 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 6.5B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 92 GB of VRAM.

はじめに

— コピー&ペーストでローカル実行

Copy-paste commands to run Mistral Small 4 119B on your machine.

Run

lms load Mistral-Small-4-119B-2603 && lms server start

Quick specs

Parameters119B (6.5B active)
Architecturemoe (MoE)
Context256K tokens
Modalitytext+vision
Min RAM46.4 GB
Rec. RAM72.6 GB (Q4_K_M)
LicenseMistral Research License
FamilyMistral Small
✓ Vision✓ Code✓ Chat✓ Reasoning

About this model

Mistral Small 4 is a powerful hybrid model capable of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families—Instruct, Reasoning (previously called Magistral), and Devstral—into a single, unified model.

  • •MoE: 128 experts, 4 active
  • •119B parameters: , with 6.5B activated per token
  • •256k context length:
  • •Multimodal input: Accepts both text and image input, with text output
  • •Instruct and Reasoning functionalities: with function calls (reasoning effort configurable per request)

関連モデル

あなたのハードウェア

検出中...

おすすめ

コスパ最良S
Mac Studio M3 Ultra 256GB~$6,999 — 38 tok/s
総合最良S
AMD Instinct MI250X 128GB~$15,000 — 109 tok/s

最適なハードウェア

Mistral Small 4 119Bのおすすめ

AMD Instinct MI250X 128GBS
128 GB
AMD Instinct MI300A 128GBS
128 GB
AMD Instinct MI250 128GBS
128 GB
Intel
Gaudi 3 128GBS
128 GB
Intel
Intel Data Center GPU Max 1550 128GBS
128 GB

このモデルを実行

Mistral Small 4 119B on AMD Instinct MI250X 128GBMistral Small 4 119B on AMD Instinct MI300A 128GBMistral Small 4 119B on AMD Instinct MI250 128GB

量子化オプション

量子化レベル別VRAM推定値

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
46.4 GB
Low—
Q3_K_S
3
58.3 GB
Low—
NVFP4
4
66.6 GB
Medium—
Q4_K_M
4
72.6 GB
Medium—
Q5_K_M
5
85.7 GB
High—
Q6_K
6
97.6 GB
High—
Q8_0
8
127.3 GB
Very High—
F16
16
244.0 GB
Maximum—

Quality benchmarks

Mistral Small 4 119B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—
HumanEval+—
Aider Polyglot—
LiveCodeBench63.6%

Reasoning

MMLU-Pro78.0%
GPQA Diamond71.2%
MATH-500—
ARC Challenge—

Source: official · 2026-03-16

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights72.6 GB
KV Cache5.4 GB
Runtime0.9 GB
Headroom0.6 GB

よくある質問

FAQ — Mistral Small 4 119B

関連項目

量子化ガイドスコアリングメソドロジーカリキュレーターを開く