gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
Global Score
84 vs 89
Hardware Fit
69 vs 96
Quality Score
91 vs 86
Hardware
gptoss · 20.9B · M… qwen3-coder:30b
MachineMac ProMacBook Pro
CPUIntel Core™ i5-10400Apple M4 Max
Cores1216
RAM32 GB64 GB
GPUAMD Radeon RX 6700 XTApple M4 Max
OSmacOS 26.5.1macOS 26.5.1
Archx64arm64
Power Modebalancedbalanced
Performance
gptoss · 20.9B · M… qwen3-coder:30b
Tokens/sec17.589.9
First chunk643 ms188 ms
TTFT7.7 s188 ms
Load time0.0 s4.0 s
Memory usage0.8 GB30.2 GB
Memory %3%47%
HW Fit Score Breakdown
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
Memory
30/30
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
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-coder:30b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
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