hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_M
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 21, 2026 · AMD RYZEN AI MAX+ 395
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
68 vs 65
Hardware Fit
69 vs 96
Quality Score
67 vs 52
Hardware
hf.co/unsloth/Qwen… richardyoung/qwyth…
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3212
RAM125 GB24 GB
GPURadeon 8060SApple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.6.1
Archx64arm64
Power Modelow-powerbalanced
Performance
hf.co/unsloth/Qwen… richardyoung/qwyth…
Tokens/sec21.125.3
First chunk571 ms397 ms
TTFT571 ms397 ms
Load time4.9 s6.3 s
Memory usage22.7 GB8.3 GB
Memory %18%34%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
20/50
TTFT
19/20
Memory
30/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
Quality
hf.co/unsloth/Qwen3.8-2…
Reasoning
12/20
Coding
10/20
Instruction
10/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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