qwen3-235b-a22b-t48-c8k:latest
OLLAMA GGUFqwen3moe · 235.1B · Q4_K_M
Aug 2, 2026 · Intel Xeon® E5-4620 0
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
Global Score
43 vs 76
Hardware Fit
28 vs 46
Quality Score
49 vs 89
Hardware
qwen3-235b-a22b-t4… gemma4:31b
MachineDell Inc. PowerEdge R820MacBook Pro
CPUIntel Xeon® E5-4620 0Apple M4 Max
Cores6416
RAM256 GB64 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M4 Max
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.3.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3-235b-a22b-t4… gemma4:31b
Tokens/sec0.722.4
First chunk6361 ms565 ms
TTFT6.4 s30.0 s
Load time0.9 s6.9 s
Memory usage134.2 GB43.9 GB
Memory %52%69%
HW Fit Score Breakdown
qwen3-235b-a22b-t48-c8k…
Speed
1/50
TTFT
3/20
Memory
24/30
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
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
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
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