qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
Sage-A1.5-Q4_K_M-GGUF:latest
OLLAMA GGUFqwen35moe · 35.5B · Q4_K_M
Oct 23, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
89 vs 86
Hardware Fit
96 vs 86
Quality Score
86 vs 86
Hardware
qwen3-coder:30b Sage-A1.5-Q4_K_M-G…
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E51
CPUApple M4 MaxAMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM64 GB31 GB
GPUApple M4 MaxNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.5.1Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-coder:30b Sage-A1.5-Q4_K_M-G…
Tokens/sec89.975.2
First chunk188 ms168 ms
TTFT188 ms168 ms
Load time4.0 s0.0 s
Memory usage30.2 GB21.4 GB
Memory %47%69%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
Sage-A1.5-Q4_K_M-GGUF:l…
Speed
50/50
TTFT
20/20
Memory
16/30
Quality
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
Sage-A1.5-Q4_K_M-GGUF:l…
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong 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