Back to leaderboard

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

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

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
77 vs 88
Hardware Fit
53 vs 94
Quality Score
87 vs 85

Hardware

qwen3.5:35b huihui-qwen3.6-35b…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-14600KFAMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM32 GB47 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Famille 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

qwen3.5:35b huihui-qwen3.6-35b…
Tokens/sec16.039.8
First chunk719 ms3 ms
TTFT719 ms479 ms
Load time17.8 sN/A
Memory usage25.0 GB24.4 GB
Memory %79%52%

HW Fit Score Breakdown

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

huihui-qwen3.6-35b-a3b-…

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

Quality

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:35b 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