Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

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

qwen2.5-coder:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
80 vs 68
Hardware Fit
60 vs 100
Quality Score
88 vs 54

Hardware

qwen/qwen3.6-35b-a3b qwen2.5-coder:1.5b
MachineSystem manufacturerLENOVO 20U30029MB
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ i5-10210U
Cores168
RAM31 GB15 GB
GPUNavi 44 [Radeon RX 9060 XT]CometLake-U GT2 [UHD Graphics]
OSUbuntu 26.04.1 LTSPop 24.04 LTS
Archx64x64
Power Modeperformancelow-power

Performance

qwen/qwen3.6-35b-a3b qwen2.5-coder:1.5b
Tokens/sec15.021.8
First chunk49 ms499 ms
TTFT759 ms499 ms
Load timeN/A4.4 s
Memory usage22.2 GB1.5 GB
Memory %71%10%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

qwen2.5-coder:1.5b

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

Quality

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

qwen2.5-coder:1.5b

Reasoning
8/20
Coding
11/20
Instruction
13/20
Structured
11/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View qwen2.5-coder:1.5b 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