Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
87 vs 67
Hardware Fit
83 vs 77
Quality Score
88 vs 63

Hardware

qwen/qwen3.8-27b llama3.2:3b
MachineMacBook ProLENOVO 20U30029MB
CPUApple M4 MaxIntel Core™ i5-10210U
Cores168
RAM128 GB15 GB
GPUApple M4 MaxCometLake-U GT2 [UHD Graphics]
OSmacOS 26.5.2Pop 24.04 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen/qwen3.8-27b llama3.2:3b
Tokens/sec29.110.0
First chunk9 ms1166 ms
TTFT650 ms1.2 s
Load timeN/A6.8 s
Memory usage21.0 GB3.8 GB
Memory %16%25%

HW Fit Score Breakdown

qwen/qwen3.8-27b

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

llama3.2:3b

Speed
27/50
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

llama3.2:3b

Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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