Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

orcarouter/Qwen3.8-27B-Uncensored:iq4_xs

OLLAMA GGUF

qwen35 · 27.3B · IQ4_XS

Excellent

Sep 11, 2026 · Intel Core™ i5-10400

Global Score
35 vs 88
Hardware Fit
45 vs 69
Quality Score
30 vs 96

Hardware

qwen3.5:35b-a3b-q4… orcarouter/Qwen3.8…
MachineMicro-Star International Co., Ltd. MS-7D98ASUS
CPUIntel Core™ i9-14900KIntel Core™ i5-10400
Cores3212
RAM128 GB16 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Todesk Virtual Display Adapter, AskLink Display Adapter (SDR), OrayIddDriver Device, NVIDIA GeForce RTX 3080
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 10 专业版 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… orcarouter/Qwen3.8…
Tokens/sec16.739.5
First chunk781 ms220 ms
TTFT30.0 s3.2 s
Load time19.9 s13.7 s
Memory usage21.8 GB14.2 GB
Memory %17%89%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
0/20
Memory
30/30

orcarouter/Qwen3.8-27B-…

Speed
50/50
TTFT
14/20
Memory
5/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

orcarouter/Qwen3.8-27B-…

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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