hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 22, 2026 · Apple M1 Pro
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
31 vs 85
Hardware Fit
37 vs 95
Quality Score
28 vs 81
Hardware
hf.co/unsloth/Qwen… gemma4:e4b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M2 Pro
Cores1010
RAM16 GB16 GB
GPUApple M1 ProApple M2 Pro
OSmacOS 26.6.2macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/unsloth/Qwen… gemma4:e4b-mlx
Tokens/sec5.447.3
First chunk5076 ms258 ms
TTFT5.1 s258 ms
Load time0.3 s5.1 s
Memory usage11.6 GB7.9 GB
Memory %72%49%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
13/50
TTFT
10/20
Memory
14/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
Quality
hf.co/unsloth/Qwen3.8-2…
Reasoning
9/20
Coding
2/20
Instruction
1/20
Structured
1/15
Math
9/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Adequate
gemma4:e4b-mlx
Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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