Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-2637 v3

Global Score
84 vs 49
Hardware Fit
97 vs 54
Quality Score
79 vs 47

Hardware

qwen3:8b qwen3.5:35b-a3b-q4…
MachineASUSDell Inc. Precision Tower 7910
CPUIntel Core™ Ultra 9 285KIntel Xeon® E5-2637 v3
Cores2416
RAM47 GB96 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsNVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:8b qwen3.5:35b-a3b-q4…
Tokens/sec208.021.6
First chunk82 ms1505 ms
TTFT1.3 s30.0 s
Load time1.5 s53.8 s
Memory usage9.6 GB22.7 GB
Memory %20%24%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
18/20
Memory
29/30

qwen3.5:35b-a3b-q4_K_M

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

Quality

qwen3:8b

Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:35b-a3b-q4_K_M

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
5/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
View qwen3:8b details | View qwen3.5:35b-a3b-q4… 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