DevStral AI

DevStral 7B

Name: DevStral 7B
Rating: 75 (185 reviews)
Author: DevStral AI

Legacy

HuggingFace

Ollama

May 2025Veröffentlicht8K TokenKontextApache 2.0Lizenz60 GutQualität

DevStral 7B (7B parameters) requires approximately 8.0 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run DevStral 7B on your machine.

Run

ollama run devstral

Quick specs

Parameters7B

Architecturedense

Context8K tokens

Modalitytext

Min RAM2.7 GB

Rec. RAM4.3 GB (Q4_K_M)

LicenseApache 2.0

FamilyDevStral

✓ Code✓ Chat

About this model

Devstral 7B is Mistral AI's specialized coding model optimized for software development tasks. Features strong code generation, completion, and understanding across multiple programming languages.

Schnellauswahl

Bestes BudgetA

Intel Arc B570 10GB~$219 — 52 tok/s

Beste GesamtwahlA

RTX 3080 Ti 12GB~$1,199 — 98 tok/s

Beste Hardware

Top-Empfehlungen für DevStral 7B

Dieses Modell ausführen

DevStral 7B on RTX 3080 Ti 12GB DevStral 7B on RTX 4070 12GB DevStral 7B on RTX 4070 Super 12GB

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	—
Q3_K_S	3	3.4 GB	Low	—
NVFP4	4	3.9 GB	Medium	—
Q4_K_M	4	4.3 GB	Medium	—
Q5_K_M	5	5.0 GB	High	—
Q6_K	6	5.7 GB	High	—
Q8_0	8	7.5 GB	Very High	—
F16	16	14.3 GB	Maximum	—

Quality benchmarks

DevStral 7B benchmark scores

Benchmark verified

Coding

SWE-bench Verified46.8%

HumanEval+—

Aider Polyglot—

LiveCodeBench—

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights4.3 GB

KV Cache2.0 GB

Runtime1.2 GB

Headroom0.6 GB

Häufig gestellte Fragen

FAQ — DevStral 7B

Siehe auch

Quantisierungsleitfaden Bewertungsmethodik Rechner öffnen