Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
59 vs 76
Hardware Fit
63 vs 82
Quality Score
58 vs 73

Hardware

qwen3.8-27b-mlx gemma4:e2b
MachineMacBook ProLENOVO 20U30029MB
CPUApple M5 MaxIntel Core™ i5-10210U
Cores188
RAM64 GB15 GB
GPUApple M5 MaxCometLake-U GT2 [UHD Graphics]
OSmacOS 27.0Pop 24.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.8-27b-mlx gemma4:e2b
Tokens/sec18.313.5
First chunk4 ms1270 ms
TTFT530 ms1.3 s
Load timeN/A13.4 s
Memory usage38.5 GB6.5 GB
Memory %60%42%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

gemma4:e2b

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

Quality

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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