qwen3-235b-a22b-t48-c8k:latest
OLLAMA GGUFqwen3moe · 235.1B · Q4_K_M
Aug 2, 2026 · Intel Xeon® E5-4620 0
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
43 vs 94
Hardware Fit
28 vs 91
Quality Score
49 vs 95
Hardware
qwen3-235b-a22b-t4… gpt-oss:20b
MachineDell Inc. PowerEdge R820Framework Desktop (AMD Ryzen AI Max 300 Series)
CPUIntel Xeon® E5-4620 0AMD RYZEN AI MAX+ 395
Cores6432
RAM256 GB64 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterAMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 Pro for Workstations 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3-235b-a22b-t4… gpt-oss:20b
Tokens/sec0.748.0
First chunk6361 ms357 ms
TTFT6.4 s2.3 s
Load time0.9 s0.2 s
Memory usage134.2 GB16.4 GB
Memory %52%26%
HW Fit Score Breakdown
qwen3-235b-a22b-t48-c8k…
Speed
1/50
TTFT
3/20
Memory
24/30
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
qwen3-235b-a22b-t48-c8k…
Reasoning
19/20
Coding
2/20
Instruction
4/20
Structured
2/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
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