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 EXL3 3.5 bpw with vLLM on 4× RTX PRO 6000
by brandonmusic
Intelligence (original model) · Artificial Analysis34with thinkingno thinking 22
Engine
- Engine
- vLLM verdictai custom (r17 Paket = RC)
- Quantization
- EXL3 TR3v4 3.5 bpw
- Model family
- GLM-5.2
- Context
- —
- Creator
- brandonmusic
- GitHub stars
- 9
- 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.
No sourced measurements for this recipe.
What you need
- Hardware
- 4 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weightsbrandonmusic/GLM-5.2-EXL3-TR3v4-3.5bpw-MTP78 MIT
- Basezai-org/GLM-5.2 MIT
- Engine
- vLLM verdictai custom (r17 Paket = RC)
Notes
What matters before you rebuild it.
- 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.