mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score

69 vs 74

Hardware Fit

50 vs 42

Quality Score

77 vs 87

Hardware

mistralai/devstral… qwen3-next:80b-a3b…

MachineMacBook AirDell Inc. PowerEdge R820

CPUApple M4Intel Xeon® E5-4650 v2

Cores1080

RAM32 GB256 GB

GPUApple M4Microsoft Basic Display Adapter

OSmacOS 26.3Microsoft Windows Server 2022 Datacenter 10.0.20348

Archarm64x64

Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3-next:80b-a3b…

Tokens/sec5.73.9

First chunk5007 ms2089 ms

TTFT5.0 s2.1 s

Load timeN/A73.3 s

Memory usage13.2 GB46.9 GB

Memory %41%18%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

qwen3-next:80b-a3b-inst…

Speed

3/50

TTFT

9/20

Memory

30/30

Quality

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3-next:80b-a3b-inst…

Reasoning

18/20

Coding

19/20

Instruction

12/20

Structured

15/15

Math

13/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

View mistralai/devstral… details | View qwen3-next:80b-a3b… details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest