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

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

Global Score
52 vs 61
Hardware Fit
75 vs 69
Quality Score
42 vs 58

Hardware

hf.co/Edge-Quant/N… qwen3.5:4b
MachineMacBook ProGigabyte Technology Co., Ltd. H170M-D3H
CPUApple M1 ProIntel Core™ i5-6500
Cores104
RAM16 GB16 GB
GPUApple M1 ProGP104 [GeForce GTX 1070]
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

hf.co/Edge-Quant/N… qwen3.5:4b
Tokens/sec43.535.7
First chunk225 ms438 ms
TTFT30.0 s5.1 s
Load time2.7 s40.1 s
Memory usage8.2 GB5.5 GB
Memory %51%35%

HW Fit Score Breakdown

hf.co/Edge-Quant/Nanbei…

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

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

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

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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