Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

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

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
78 vs 90
Hardware Fit
86 vs 100
Quality Score
74 vs 86

Hardware

qwen3:8b qwen3.6-35b-a3b-cl…
Machine—MacBook Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M4 Max
Cores2416
RAM64 GB128 GB
GPUNVIDIA GeForce RTX 4060 TiApple M4 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:8b qwen3.6-35b-a3b-cl…
Tokens/sec48.578.1
First chunk202 ms7 ms
TTFT4.3 s138 ms
Load time4.2 sN/A
Memory usage5.5 GB23.9 GB
Memory %9%19%

HW Fit Score Breakdown

qwen3:8b

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

qwen3.6-35b-a3b-claude-…

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

Quality

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

qwen3.6-35b-a3b-claude-…

Reasoning
18/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:8b details | View qwen3.6-35b-a3b-cl… 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