hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_M
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 21, 2026 · AMD RYZEN AI MAX+ 395
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
68 vs 67
Hardware Fit
69 vs 67
Quality Score
67 vs 67
Hardware
hf.co/unsloth/Qwen… codestral:22b
MachineAZW GTR ProNVIDIA NVIDIA_DGX_Spark
CPUAMD RYZEN AI MAX+ 395Cortex-X925
Cores3220
RAM125 GB122 GB
GPURadeon 8060SDevice 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance
Performance
hf.co/unsloth/Qwen… codestral:22b
Tokens/sec21.117.2
First chunk571 ms129 ms
TTFT571 ms129 ms
Load time4.9 s11.6 s
Memory usage22.7 GB18.9 GB
Memory %18%16%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
20/50
TTFT
19/20
Memory
30/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
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
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak 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