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

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
35 vs 78
Hardware Fit
45 vs 86
Quality Score
30 vs 74

Hardware

qwen3.5:35b-a3b-q4… qwen3:8b
MachineMicro-Star International Co., Ltd. MS-7D98—
CPUIntel Core™ i9-14900KAMD Ryzen 9 3900X 12-Core Processor
Cores3224
RAM128 GB64 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000NVIDIA GeForce RTX 4060 Ti
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… qwen3:8b
Tokens/sec16.748.5
First chunk781 ms202 ms
TTFT30.0 s4.3 s
Load time19.9 s4.2 s
Memory usage21.8 GB5.5 GB
Memory %17%9%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

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

qwen3:8b

Speed
50/50
TTFT
6/20
Memory
30/30

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

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:35b-a3b-q4… details | View qwen3:8b 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