Back to leaderboard

qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive

OPENAI GGUF
Good

Apr 21, 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
62 vs 68
Hardware Fit
100 vs 59
Quality Score
45 vs 72

Hardware

qwen3.5-35b-a3b-un… 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

qwen3.5-35b-a3b-un… qwen2.5-coder:7b
Tokens/sec67.934.4
First chunk50 ms1991 ms
TTFT75 ms2.0 s
Load time0.0 s40.6 s
Memory usage0.0 GB5.0 GB
Memory %0%8%

HW Fit Score Breakdown

qwen3.5-35b-a3b-uncenso…

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

qwen2.5-coder:7b

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

Quality

qwen3.5-35b-a3b-uncenso…

Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
0/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor Math: Adequate 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 qwen3.5-35b-a3b-un… 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