Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

Global Score
57 vs 35
Hardware Fit
61 vs 45
Quality Score
55 vs 30

Hardware

qwen3.5:9b qwen3.5:35b-a3b-q4…
MachineAZW GTR ProMicro-Star International Co., Ltd. MS-7D98
CPUAMD RYZEN AI MAX+ 395Intel Core™ i9-14900K
Cores3232
RAM125 GB128 GB
GPUAMD Radeon 8060SIntel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:9b qwen3.5:35b-a3b-q4…
Tokens/sec30.316.7
First chunk205 ms781 ms
TTFT8.7 s30.0 s
Load time5.6 s19.9 s
Memory usage18.8 GB21.8 GB
Memory %15%17%

HW Fit Score Breakdown

qwen3.5:9b

Speed
30/50
TTFT
1/20
Memory
30/30

qwen3.5:35b-a3b-q4_K_M

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

Quality

qwen3.5:9b

Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong 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 qwen3.5:9b 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