2× DGX Spark
36.1tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinking
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- Non-commercial
- License unclear
Local AI · Recipe · 2× DGX Spark
GLM-5.3-Flash 320B EXL3 4 bpw with ExLlamaV3 on 2× DGX Spark
by tonyd2wild
Engine
- Engine
- ExLlamaV3 (via vLLM)
- Quantization
- EXL3 4bpw
- Model family
- GLM-5.3-Flash
- Context
- 1,048,576
- Parameters
- 320B MoE
- Creator
- tonyd2wild
- GitHub stars
- 6
- Repo updated
- Sep 20, 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
- 2 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsMia-AiLab/GLM-5.3-Flash-EXL3-TR3-4bpw other
- otherbrandonmusic/GLM-5.3-Flash-tr3-4bpw other
- Draft modelincoai/GLM-5.3-Flash-DFlash2 Non-commercial · CC-BY-NC-ND-4.0
- Engine
- ExLlamaV3 (via vLLM)
- Context
- 1,048,576 tokens
Related recipes
4× DGX Spark
34.1tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinking
- Custom kernel required
- Non-commercial
4× DGX Spark
31.5tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinking
- Custom kernel required
- Non-commercial
1× DGX Spark
19.5tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinkingOriginal model's value. Heavily compressed (~2.3 bit), intelligence is likely much lower.
- ≤ 3 bit: quantization may cost quality
- Experimental
- Custom kernel required
- Non-commercial
2× RTX 3090
18.1tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence42with thinking
- ≤ 3 bit: quantization may cost quality
- Partly in system RAM
2× DGX Spark
17.9tok/sEveryday
1 request, prose prompt, with DFlash2 Source
Intelligence42with thinking
- Custom kernel required
- Non-commercial
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.