Back to leaderboard

qwen/qwen3-coder-30b

LM-STUDIO GGUF

qwen3moe · 30B · Q4_K_M

Not Rec.

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
85 vs 82
Hardware Fit
79 vs 81
Quality Score
88 vs 82

Hardware

qwen/qwen3-coder-30b qwen3.5:9b
MachineGMKtec EVO-X3AZW GTR Pro
CPUAMD RYZEN AI MAX+ 395AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores3232
RAM120 GB125 GB
GPUAMD Radeon(TM) 8060S GraphicsIntegrated / Apple Silicon
OSMicrosoft Windows 11 Pro 10.0.26300Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen/qwen3-coder-30b qwen3.5:9b
Tokens/sec42.330.8
First chunk10 ms195 ms
TTFT707 ms195 ms
Load time167.7 s6.8 s
Memory usage70.3 GB18.8 GB
Memory %59%15%

HW Fit Score Breakdown

qwen/qwen3-coder-30b

Speed
40/50
TTFT
18/20
Memory
21/30

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

Quality

qwen/qwen3-coder-30b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3-coder-30b details | View qwen3.5:9b 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