mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score

73 vs 70

Hardware Fit

64 vs 39

Quality Score

77 vs 83

Hardware

mistralai/devstral… qwen3-next-80b-t48…

MachineMacBook ProDell Inc. PowerEdge R820

CPUApple M1 ProIntel Xeon® E5-4620 0

Cores1064

RAM32 GB256 GB

GPUApple M1 ProMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter

OSmacOS 15.6.1Microsoft Windows Server 2022 Datacenter 10.0.20348

Archarm64x64

Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3-next-80b-t48…

Tokens/sec11.93.0

First chunk7 ms3265 ms

TTFT1.1 s3.3 s

Load timeN/A82.1 s

Memory usage19.7 GB46.9 GB

Memory %62%18%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

qwen3-next-80b-t48:latest

Speed

3/50

TTFT

6/20

Memory

30/30

Quality

mistralai/devstral-smal…

Reasoning

17/20

Coding

16/20

Instruction

13/20

Structured

14/15

Math

7/15

Multilingual

10/10

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

qwen3-next-80b-t48:latest

Reasoning

18/20

Coding

18/20

Instruction

9/20

Structured

15/15

Math

13/15

Multilingual

10/10

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

View mistralai/devstral… details | View qwen3-next-80b-t48… 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