Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 19, 2026 · Apple M4 Max

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Core™ i9-14900K

Global Score
89 vs 35
Hardware Fit
96 vs 45
Quality Score
86 vs 30

Hardware

qwen3-coder:30b qwen3.5:35b-a3b-q4…
MachineMacBook ProMicro-Star International Co., Ltd. MS-7D98
CPUApple M4 MaxIntel Core™ i9-14900K
Cores1632
RAM64 GB128 GB
GPUApple M4 MaxIntel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSmacOS 26.5.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-coder:30b qwen3.5:35b-a3b-q4…
Tokens/sec89.916.6
First chunk188 ms767 ms
TTFT188 ms30.0 s
Load time4.0 s0.4 s
Memory usage30.2 GB21.8 GB
Memory %47%17%

HW Fit Score Breakdown

qwen3-coder:30b

Speed
50/50
TTFT
20/20
Memory
26/30

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
0/20
Memory
30/30

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

qwen3.5:35b-a3b-q4_K_M

Reasoning
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
View qwen3-coder:30b details | View qwen3.5:35b-a3b-q4… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest