unsloth
GLM 4 32B 0414
GLM 4 32B 0414 is a 32.6B dense glm4 model from unsloth. Configured context length is 32,768 tokens. License: mit. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters32.6B
Context32K
Attentiongqa
Licensemit
61 layers · 2 KV heads · head dim 128 · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 60.7 GB | Hugging Face file bytes |
| UD-Q8_K_XL | 36.8 GB | Hugging Face file bytes |
| Q8_0 | 32.2 GB | Hugging Face file bytes |
| UD-Q6_K_XL | 26.8 GB | Hugging Face file bytes |
| Q6_K | 24.9 GB | Hugging Face file bytes |
| UD-Q5_K_XL | 21.5 GB | Hugging Face file bytes |
| Q5_K_M | 21.5 GB | Hugging Face file bytes |
| Q5_K_S | 21.0 GB | Hugging Face file bytes |
| UD-Q4_K_XL | 18.6 GB | Hugging Face file bytes |
| Q4_K_M | 18.3 GB | Hugging Face file bytes |
| Q4_K_S | 17.4 GB | Hugging Face file bytes |
| IQ4_NL | 17.3 GB | Hugging Face file bytes |
| IQ4_XS | 16.4 GB | Hugging Face file bytes |
| Q4_1 | 19.1 GB | Hugging Face file bytes |
| Q4_0 | 17.4 GB | Hugging Face file bytes |
| UD-Q3_K_XL | 15.2 GB | Hugging Face file bytes |
| Q3_K_M | 14.8 GB | Hugging Face file bytes |
| Q3_K_S | 13.4 GB | Hugging Face file bytes |
| UD-IQ3_XXS | 12.1 GB | Hugging Face file bytes |
| UD-Q2_K_XL | 11.9 GB | Hugging Face file bytes |
| Q2_K | 23.1 GB | Hugging Face file bytes |
| UD-IQ2_XXS | 8.63 GB | Hugging Face file bytes |
| UD-IQ1_M | 7.71 GB | Hugging Face file bytes |
| UD-IQ1_S | 7.17 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Partial offload | Q4_K_M | 3.3–4.5 |
| GeForce RTX 3060 12GB | Tight fit | UD-IQ2_XXS | 20–28 |
| GeForce RTX 4060 Ti 16GB | Tight fit | Q3_K_S | 11–15 |
| GeForce RTX 4090 | Tight fit | Q5_K_S | 24–33 |
| GeForce RTX 5090 | Tight fit | UD-Q6_K_XL | 34–46 |
| Apple M4 Pro | Tight fit | IQ4_XS | 8.3–11 |
| Apple M5 | Tight fit | UD-IQ2_XXS | 8.6–12 |
| CPU only · DDR5-5600 | Runs on CPU | UD-Q5_K_XL | 2.1–2.8 |
Smallest devices that fit it fully
- GeForce RTX 3080 10GB — Tight fit, UD-IQ1_M, 48–65 tok/s
- Intel Arc B570 — Tight fit, UD-IQ1_M, 24–32 tok/s
- GeForce RTX 2080 Ti — Tight fit, UD-IQ2_XXS, 35–47 tok/s
- GeForce GTX 1080 Ti — Tight fit, UD-IQ2_XXS, 27–37 tok/s
- GeForce RTX 5070 — Tight fit, UD-IQ2_XXS, 38–52 tok/s
- GeForce RTX 4070 Ti — Tight fit, UD-IQ2_XXS, 28–39 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (Q3_K_S).
llama.cpp
llama-server -hf unsloth/GLM-4-32B-0414-GGUF:Q3_K_S -c 8192 -ngl 61
No matching name in the Ollama library snapshot.
LM Studio
lms get unsloth/GLM-4-32B-0414-GGUF # Then load quant Q3_K_S