Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score
70 vs 73
Hardware Fit
73 vs 64
Quality Score
68 vs 77

Hardware

llama3.1:8b-instru… mistralai/devstral…
Machine—MacBook Pro
CPUC1-ProApple M1 Pro
Cores010
RAM11 GB32 GB
GPUIntegrated / UnknownApple M1 Pro
OSunknown unknownmacOS 15.6.1
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… mistralai/devstral…
Tokens/sec6.511.9
First chunk950 ms7 ms
TTFT950 ms1.1 s
Load time11.5 sN/A
Memory usage4.4 GB19.7 GB
Memory %38%62%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

mistralai/devstral-smal…

Speed
25/50
TTFT
20/20
Memory
19/30

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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

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