lmstudio-community/meta-llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q4_K_M

Good

Mar 5, 2026 · Apple M4 Pro

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score

78 vs 73

Hardware Fit

100 vs 64

Quality Score

69 vs 77

Hardware

lmstudio-community… mistralai/devstral…

MachineMac miniMacBook Pro

CPUApple M4 ProApple M1 Pro

Cores1410

RAM64 GB32 GB

GPUApple M4 ProApple M1 Pro

OSmacOS 15.7.4macOS 15.6.1

Archarm64arm64

Power Modebalancedbalanced

Performance

lmstudio-community… mistralai/devstral…

Tokens/sec46.011.9

First chunk245 ms7 ms

TTFT245 ms1.1 s

Load timeN/AN/A

Memory usage4.6 GB19.7 GB

Memory %7%62%

HW Fit Score Breakdown

lmstudio-community/meta…

Speed

50/50

TTFT

20/20

Memory

30/30

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

Quality

lmstudio-community/meta…

Reasoning

11/20

Coding

15/20

Instruction

14/20

Structured

15/15

Math

4/15

Multilingual

10/10

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

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

View lmstudio-community… details | View mistralai/devstral… 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