Back to leaderboard

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_S

Not Rec.

Apr 20, 2026 · Apple M2 Max

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
82 vs 68
Hardware Fit
80 vs 59
Quality Score
83 vs 72

Hardware

qwen3.6-35b-a3b qwen2.5-coder:7b
MachineMac StudioASUS
CPUApple M2 MaxIntel Gen Intel® Core™ i7-13700K
Cores1224
RAM96 GB64 GB
GPUApple M2 MaxNVIDIA GeForce RTX 3070
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3.6-35b-a3b qwen2.5-coder:7b
Tokens/sec55.234.4
First chunk4 ms1991 ms
TTFT30.0 s2.0 s
Load timeN/A40.6 s
Memory usage30.3 GB5.0 GB
Memory %32%8%

HW Fit Score Breakdown

qwen3.6-35b-a3b

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

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

qwen3.6-35b-a3b

Reasoning
18/20
Coding
10/20
Instruction
18/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.6-35b-a3b details | View qwen2.5-coder:7b 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