Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
81 vs 76
Hardware Fit
68 vs 82
Quality Score
87 vs 73

Hardware

qwen/qwen3.8-27b gemma4:e2b
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 Modebalancedperformance

Performance

qwen/qwen3.8-27b gemma4:e2b
Tokens/sec16.413.5
First chunk5 ms1270 ms
TTFT742 ms1.3 s
Load timeN/A13.4 s
Memory usage38.5 GB6.5 GB
Memory %30%42%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
18/50
TTFT
20/20
Memory
30/30

gemma4:e2b

Speed
35/50
TTFT
20/20
Memory
27/30

Quality

qwen/qwen3.8-27b

Reasoning
17/20
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

gemma4:e2b

Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong 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