Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_0

Good

Feb 28, 2026 · Apple M4 Pro

Global Score
89 vs 72
Hardware Fit
95 vs 100
Quality Score
87 vs 60

Hardware

qwen/qwen3-8b mistral:latest
MachineMac miniMac Mini
CPUApple M4 ProApple M4 Pro
Cores1414
RAM64 GB64 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 15.7.4
Archarm64arm64
Power Modebalancedunknown

Performance

qwen/qwen3-8b mistral:latest
Tokens/sec33.454.3
First chunk257 msN/A
TTFT257 ms124 ms
Load timeN/A0.0 s
Memory usage4.3 GB9.9 GB
Memory %7%15%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

mistral:latest

Speed
40/50
TTFT
30/20
Memory
30/30

Quality

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

mistral:latest

Reasoning
8/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen/qwen3-8b details | View mistral:latest 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