hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0
OLLAMA GGUFllama · 3.93B · unknown
Aug 22, 2026 · Apple M1 Pro
qwen/qwen3.6-35b-a3b:2
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
52 vs 73
Hardware Fit
75 vs 50
Quality Score
42 vs 83
Hardware
hf.co/Edge-Quant/N… qwen/qwen3.6-35b-a…
MachineMacBook ProSystem manufacturer
CPUApple M1 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M1 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.6.2Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
hf.co/Edge-Quant/N… qwen/qwen3.6-35b-a…
Tokens/sec43.510.5
First chunk225 ms4 ms
TTFT30.0 s1.7 s
Load time2.7 sN/A
Memory usage8.2 GB21.4 GB
Memory %51%69%
HW Fit Score Breakdown
hf.co/Edge-Quant/Nanbei…
Speed
50/50
TTFT
0/20
Memory
25/30
qwen/qwen3.6-35b-a3b:2
Speed
16/50
TTFT
18/20
Memory
16/30
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
qwen/qwen3.6-35b-a3b:2
Reasoning
16/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest