Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

qwen3.8-27b-uncensored-ymq-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

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

Global Score
59 vs 84
Hardware Fit
69 vs 81
Quality Score
54 vs 85

Hardware

qwen3.5:35b-a3b qwen3.8-27b-uncens…
MachineMacBook ProGigabyte Technology Co., Ltd. X570 AORUS PRO
CPUApple M4 ProAMD Ryzen 5 5600X 6-Core Processor
Cores1412
RAM48 GB32 GB
GPUApple M4 ProNVIDIA GeForce RTX 5070 Ti
OSmacOS 26.3.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b qwen3.8-27b-uncens…
Tokens/sec30.518.3
First chunk333 ms9 ms
TTFT30.0 s522 ms
Load time9.8 s7.7 s
Memory usage25.1 GB14.9 GB
Memory %52%47%

HW Fit Score Breakdown

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

qwen3.8-27b-uncensored-…

Speed
35/50
TTFT
20/20
Memory
26/30

Quality

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong

qwen3.8-27b-uncensored-…

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:35b-a3b details | View qwen3.8-27b-uncens… 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