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

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
52 vs 68
Hardware Fit
75 vs 59
Quality Score
42 vs 72

Hardware

hf.co/Edge-Quant/N… qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M1 ProIntel Gen Intel® Core™ i7-13700K
Cores1024
RAM16 GB64 GB
GPUApple M1 ProNVIDIA GeForce RTX 3070
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

hf.co/Edge-Quant/N… qwen2.5-coder:7b
Tokens/sec43.534.4
First chunk225 ms1991 ms
TTFT30.0 s2.0 s
Load time2.7 s40.6 s
Memory usage8.2 GB5.0 GB
Memory %51%8%

HW Fit Score Breakdown

hf.co/Edge-Quant/Nanbei…

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

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

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

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View hf.co/Edge-Quant/N… details | View qwen2.5-coder:7b 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