gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
Global Score
84 vs 70
Hardware Fit
69 vs 93
Quality Score
91 vs 60
Hardware
gptoss · 20.9B · M… qwen3.5-2b-mlx
MachineMac ProMacBook Air
CPUIntel Core™ i5-10400Apple M4
Cores1210
RAM32 GB32 GB
GPUAMD Radeon RX 6700 XTApple M4
OSmacOS 26.5.1macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
gptoss · 20.9B · M… qwen3.5-2b-mlx
Tokens/sec17.532.9
First chunk643 ms3096 ms
TTFT7.7 s3.1 s
Load time0.0 sN/A
Memory usage0.8 GB2.5 GB
Memory %3%8%
HW Fit Score Breakdown
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
Memory
30/30
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
Quality
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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