qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest