hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 22, 2026 · Apple M1 Pro
nemotron-3-nano:latest
OLLAMA GGUFnemotron_h_moe · 31.6B · Q4_K_M
Mar 27, 2026 · AMD RYZEN AI MAX+ 395
Global Score
31 vs 89
Hardware Fit
37 vs 100
Quality Score
28 vs 84
Hardware
hf.co/unsloth/Qwen… nemotron-3-nano:la…
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
hf.co/unsloth/Qwen… nemotron-3-nano:la…
Tokens/sec5.465.2
First chunk5076 ms295 ms
TTFT5.1 s295 ms
Load time0.3 s8.7 s
Memory usage11.6 GB26.0 GB
Memory %72%21%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
13/50
TTFT
10/20
Memory
14/30
nemotron-3-nano:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
hf.co/unsloth/Qwen3.8-2…
Reasoning
9/20
Coding
2/20
Instruction
1/20
Structured
1/15
Math
9/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Adequate
nemotron-3-nano:latest
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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