Back to leaderboard

hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0

OLLAMA GGUF

llama · 3.93B · unknown

Not Rec.

Aug 22, 2026 · Apple M1 Pro

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
52 vs 82
Hardware Fit
75 vs 81
Quality Score
42 vs 82

Hardware

hf.co/Edge-Quant/N… qwen3.5:9b
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProAMD Radeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

hf.co/Edge-Quant/N… qwen3.5:9b
Tokens/sec43.530.8
First chunk225 ms195 ms
TTFT30.0 s195 ms
Load time2.7 s5.2 s
Memory usage8.2 GB18.8 GB
Memory %51%15%

HW Fit Score Breakdown

hf.co/Edge-Quant/Nanbei…

Speed
50/50
TTFT
0/20
Memory
25/30

qwen3.5:9b

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

Quality

hf.co/Edge-Quant/Nanbei…

Reasoning
13/20
Coding
1/20
Instruction
7/20
Structured
1/15
Math
13/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate

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 hf.co/Edge-Quant/N… 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