4× RTX PRO 6000
81.7tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
Local AI · Recipe · 4× RTX PRO 6000
GLM-5.2 753B EXL3 with vLLM on 4× RTX PRO 6000
GLM-5.2 753B EXL3 with vLLM on 4× RTX PRO 6000: 101 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by brandonmusic
Intelligence (original model) · Artificial Analysis34with thinkingno thinking 22
≤ 3 bit: quantization may cost quality
Engine
- Engine
- vLLM
- Quantization
- EXL3 TR3 Experten + 6-bpw Dense + nvfp4_ds_mla KV
- Model family
- GLM-5.2
- Context
- 524,288
- Parameters
- 753B MoE (laut Kontext)
- Creator
- brandonmusic
- GitHub stars
- 2
- Repo updated
- Aug 23, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Decode · 1 request
Prefill by context
What you need
- Hardware
- 4 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weightsbrandonmusic/GLM-5.2-EXL3-DENSE6-MTP78 MIT
- Basebrandonmusic/GLM-5.2-EXL3-TR3-3.0bpw MIT
- MTPmalaiwah/GLM-5.2-EXL3-TR3-MTP78 MIT
- Basezai-org/GLM-5.2 MIT
- Engine
- vLLM
- Context
- 524,288 tokens
Notes
What matters before you rebuild it.
- ≤ 3 bit: quantization may cost qualityAt 3 bit and below the model may answer noticeably worse than the original. The intelligence number refers to the original.
- Custom runtime
Sources
Related recipes
4× RTX PRO 6000
70.7tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
4× RTX PRO 6000
64tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
4× RTX PRO 6000
58.5tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligenceno independent value
- Custom kernel required
4× RTX PRO 6000
104tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
4× RTX PRO 6000
92.5tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligenceno independent value
Local AI in your company?
In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.