Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
57 vs 88
Hardware Fit
61 vs 85
Quality Score
55 vs 89

Hardware

qwen3.5:9b huihui-qwen3.6-35b…
MachineAZW GTR ProGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 5 5600X 6-Core Processor
Cores3212
RAM125 GB47 GB
GPUAMD Radeon 8060SAD106 [GeForce RTX 4060 Ti]
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modelow-powerlow-power

Performance

qwen3.5:9b huihui-qwen3.6-35b…
Tokens/sec30.337.7
First chunk205 ms18 ms
TTFT8.7 s2.9 s
Load time5.6 sN/A
Memory usage18.8 GB26.1 GB
Memory %15%56%

HW Fit Score Breakdown

qwen3.5:9b

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

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

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

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:9b details | View huihui-qwen3.6-35b… 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