Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

mistral:7b

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
87 vs 70
Hardware Fit
83 vs 94
Quality Score
88 vs 60

Hardware

qwen/qwen3.8-27b mistral:7b
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM128 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b mistral:7b
Tokens/sec29.122.5
First chunk9 ms252 ms
TTFT650 ms252 ms
Load timeN/A0.7 s
Memory usage21.0 GB10.1 GB
Memory %16%32%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

mistral:7b

Speed
44/50
TTFT
20/20
Memory
30/30

Quality

qwen/qwen3.8-27b

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

mistral:7b

Reasoning
8/20
Coding
12/20
Instruction
14/20
Structured
14/15
Math
4/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen/qwen3.8-27b details | View mistral:7b 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