Back to leaderboard

qwen3.8-27b-claude-opus-reasoning-distilled

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Aug 20, 2026 · Apple M4 Max

cogito:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
80 vs 77
Hardware Fit
63 vs 92
Quality Score
87 vs 70

Hardware

qwen3.8-27b-claude… cogito:8b
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

qwen3.8-27b-claude… cogito:8b
Tokens/sec24.021.0
First chunk20 ms312 ms
TTFT4.5 s312 ms
Load timeN/A0.8 s
Memory usage15.7 GB10.4 GB
Memory %12%33%

HW Fit Score Breakdown

qwen3.8-27b-claude-opus…

Speed
27/50
TTFT
6/20
Memory
30/30

cogito:8b

Speed
42/50
TTFT
20/20
Memory
30/30

Quality

qwen3.8-27b-claude-opus…

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

cogito:8b

Reasoning
14/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.8-27b-claude… details | View cogito:8b 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