Back to leaderboard

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
77 vs 80
Hardware Fit
53 vs 60
Quality Score
87 vs 88

Hardware

qwen3.5:35b qwen/qwen3.6-35b-a3b
MachineASUSSystem manufacturer
CPUIntel Core™ i5-14600KFAMD Ryzen 7 5800X 8-Core Processor
Cores2016
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Famille 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3.5:35b qwen/qwen3.6-35b-a3b
Tokens/sec16.015.0
First chunk719 ms49 ms
TTFT719 ms759 ms
Load time17.8 sN/A
Memory usage25.0 GB22.2 GB
Memory %79%71%

HW Fit Score Breakdown

qwen3.5:35b

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

qwen/qwen3.6-35b-a3b

Speed
25/50
TTFT
20/20
Memory
15/30

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

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:35b details | View qwen/qwen3.6-35b-a3b 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