Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Xeon® E5-2637 v3

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

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

Global Score
81 vs 78
Hardware Fit
72 vs 86
Quality Score
85 vs 74

Hardware

qwen3.5:35b-a3b-q4… qwen3:8b
MachineDell Inc. Precision Tower 7910—
CPUIntel Xeon® E5-2637 v3AMD Ryzen 9 3900X 12-Core Processor
Cores1624
RAM96 GB64 GB
GPUNVIDIA GeForce RTX 5060 TiNVIDIA GeForce RTX 4060 Ti
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… qwen3:8b
Tokens/sec24.248.5
First chunk1607 ms202 ms
TTFT1.6 s4.3 s
Load time66.4 s4.2 s
Memory usage22.7 GB5.5 GB
Memory %24%9%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
28/50
TTFT
14/20
Memory
30/30

qwen3:8b

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

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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