Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

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

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-2637 v3

Global Score
82 vs 49
Hardware Fit
81 vs 54
Quality Score
82 vs 47

Hardware

qwen3.5:9b qwen3.5:35b-a3b-q4…
MachineAZW GTR ProDell Inc. Precision Tower 7910
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SIntel Xeon® E5-2637 v3
Cores3216
RAM125 GB96 GB
GPUIntegrated / Apple SiliconNVIDIA GeForce RTX 5060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5:9b qwen3.5:35b-a3b-q4…
Tokens/sec30.821.6
First chunk195 ms1505 ms
TTFT195 ms30.0 s
Load time6.8 s53.8 s
Memory usage18.8 GB22.7 GB
Memory %15%24%

HW Fit Score Breakdown

qwen3.5:9b

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

qwen3.5:35b-a3b-q4_K_M

Speed
24/50
TTFT
0/20
Memory
30/30

Quality

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

qwen3.5:35b-a3b-q4_K_M

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
5/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
View qwen3.5:9b 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