qwen3-vl:8b
OLLAMA GGUFqwen3vl · 8.8B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
OPENAI GGUFApr 21, 2026 · Apple M2 Max
Global Score
72 vs 62
Hardware Fit
89 vs 100
Quality Score
64 vs 45
Hardware
qwen3-vl:8b qwen3.5-35b-a3b-un…
MachineHP HP Z8 G4 WorkstationMac Studio
CPUIntel Xeon® Gold 6230Apple M2 Max
Cores8012
RAM252 GB96 GB
GPUTU104GL [Quadro RTX 5000]Apple M2 Max
OSUbuntu 24.04.4 LTSmacOS 26.1
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3-vl:8b qwen3.5-35b-a3b-un…
Tokens/sec68.267.9
First chunk285 ms50 ms
TTFT2.0 s75 ms
Load time42.4 s0.0 s
Memory usage7.1 GB0.0 GB
Memory %3%0%
HW Fit Score Breakdown
qwen3-vl:8b
Speed
50/50
TTFT
9/20
Memory
30/30
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3-vl:8b
Reasoning
16/20
Coding
3/20
Instruction
10/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong
qwen3.5-35b-a3b-uncenso…
Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
0/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor Math: Adequate 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