Back to leaderboard

qwen3.5-35b-a3b-t24-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
34 vs 82
Hardware Fit
45 vs 81
Quality Score
29 vs 82

Hardware

qwen3.5-35b-a3b-t2… qwen3.5:9b
MachineMicro-Star International Co., Ltd. MS-7D98AZW GTR Pro
CPUIntel Core™ i9-14900KAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores3232
RAM128 GB125 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Integrated / Apple Silicon
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3.5-35b-a3b-t2… qwen3.5:9b
Tokens/sec16.530.8
First chunk772 ms195 ms
TTFT30.0 s195 ms
Load time11.6 s6.8 s
Memory usage22.0 GB18.8 GB
Memory %17%15%

HW Fit Score Breakdown

qwen3.5-35b-a3b-t24-c8k…

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

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5-35b-a3b-t24-c8k…

Reasoning
9/20
Coding
0/20
Instruction
4/20
Structured
1/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5-35b-a3b-t2… details | View qwen3.5:9b 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