Ornith-1.0-35B GGUF size and VRAM requirements
unsloth/Ornith-1.0-35B-GGUF is a very large language model with 34.66 billion parameters, built on the qwen35moe architecture. It is released under the mit license and has been downloaded 110,700 times.
To run unsloth/Ornith-1.0-35B-GGUF locally at a 4,096-token context, its quantized versions need between 1.72 GB (F16, lowest quality) and 66.33 GB (BF16, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is F32, needing about 2.54 GB. That means unsloth/Ornith-1.0-35B-GGUF fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.
Available GGUF quantizations for unsloth/Ornith-1.0-35B-GGUF include F16, F32, IQ1_S, IQ1_M, IQ2_XXS, IQ2_M, Q2_K_XL, IQ3_XXS, IQ3_S, Q3_K_M, Q3_K_XL, IQ4_XS, IQ4_NL, Q4_K_S, GGUF, Q4_K_M, Q4_K_XL, Q5_K_S, Q5_K_M, Q5_K_XL, Q6_K, Q6_K_XL, Q8_0, Q8_K_XL, BF16. The model supports a native context length of up to 262,144 tokens; a longer context grows the KV cache and the memory needed.
GGUF file size and memory by quantization
Compare real GGUF weight sizes, estimated KV cache and total memory for Q4, Q5, Q8 and every quantization published in this repository.
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| F16 | 0.21 | Very low | 0.84 GB | 0.08 GB | 1.72 GB | 477.6 t/s | Fits in VRAM |
| F32 | 0.41 | Very low | 1.66 GB | 0.08 GB | 2.54 GB | 240.4 t/s | Fits in VRAM |
| IQ1_S | 2.43 | Very low | 9.8 GB | 0.08 GB | 10.68 GB | 5.1 t/s | Offload |
| IQ1_M | 2.55 | Very low | 10.29 GB | 0.08 GB | 11.16 GB | 4.9 t/s | Offload |
| IQ2_XXS | 2.65 | Low | 10.71 GB | 0.08 GB | 11.59 GB | 4.7 t/s | Offload |
| IQ2_M | 2.67 | Low | 10.77 GB | 0.08 GB | 11.65 GB | 4.6 t/s | Offload |
| Q2_K_XL | 2.83 | Low | 11.41 GB | 0.08 GB | 12.29 GB | 4.4 t/s | Offload |
| IQ3_XXS | 3.17 | Low | 12.8 GB | 0.08 GB | 13.68 GB | 3.9 t/s | Offload |
| IQ3_S | 3.46 | Fair | 13.96 GB | 0.08 GB | 14.83 GB | 3.6 t/s | Offload |
| Q3_K_M | 3.85 | Fair | 15.53 GB | 0.08 GB | 16.41 GB | 3.2 t/s | Offload |
| Q3_K_XL | 3.88 | Fair | 15.65 GB | 0.08 GB | 16.53 GB | 3.2 t/s | Offload |
| IQ4_XS | 4.1 | Fair | 16.56 GB | 0.08 GB | 17.44 GB | 3.0 t/s | Offload |
| IQ4_NL | 4.18 | Fair | 16.87 GB | 0.08 GB | 17.75 GB | 3.0 t/s | Offload |
| Q4_K_S | 4.82 | Good | 19.46 GB | 0.08 GB | 20.34 GB | 2.6 t/s | Offload |
| GGUF | 5.0 | Very good | 20.18 GB | 0.08 GB | 21.06 GB | 2.5 t/s | Offload |
| Q4_K_M | 5.11 | Very good | 20.61 GB | 0.08 GB | 21.49 GB | 2.4 t/s | Offload |
| Q4_K_XL | 5.15 | Very good | 20.79 GB | 0.08 GB | 21.67 GB | 2.4 t/s | Offload |
| Q5_K_S | 5.76 | Very good | 23.23 GB | 0.08 GB | 24.11 GB | — | Insufficient |
| Q5_K_M | 6.11 | Very good | 24.64 GB | 0.08 GB | 25.52 GB | — | Insufficient |
| Q5_K_XL | 6.12 | Very good | 24.71 GB | 0.08 GB | 25.58 GB | — | Insufficient |
| Q6_K | 6.76 | Excellent | 27.3 GB | 0.08 GB | 28.17 GB | — | Insufficient |
| Q6_K_XL | 7.35 | Excellent | 29.66 GB | 0.08 GB | 30.53 GB | — | Insufficient |
| Q8_0 | 8.52 | Excellent | 34.37 GB | 0.08 GB | 35.25 GB | — | Insufficient |
| Q8_K_XL | 8.82 | Excellent | 35.58 GB | 0.08 GB | 36.46 GB | — | Insufficient |
| BF16 | 16.22 | Excellent | 65.45 GB | 0.08 GB | 66.33 GB | — | Insufficient |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
What kind of model is unsloth/Ornith-1.0-35B-GGUF?
unsloth/Ornith-1.0-35B-GGUF is a language model with 34.66 billion parameters, based on the qwen35moe architecture. It is released under the mit license and distributed as GGUF files for local inference.
How much VRAM do you need to run unsloth/Ornith-1.0-35B-GGUF?
You need about 2.54 GB of VRAM to run unsloth/Ornith-1.0-35B-GGUF entirely on the GPU using the F32 quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run unsloth/Ornith-1.0-35B-GGUF on an 8 GB GPU?
Yes. With 8 GB of VRAM you can run unsloth/Ornith-1.0-35B-GGUF fully on the GPU using F32 (about 2.54 GB).
Can I run unsloth/Ornith-1.0-35B-GGUF on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run unsloth/Ornith-1.0-35B-GGUF fully on the GPU using IQ3_S (about 14.83 GB).
Can I run unsloth/Ornith-1.0-35B-GGUF on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run unsloth/Ornith-1.0-35B-GGUF fully on the GPU using Q4_K_XL (about 21.67 GB).
What context length does unsloth/Ornith-1.0-35B-GGUF support?
unsloth/Ornith-1.0-35B-GGUF supports a native context length of up to 262,144 tokens. A longer context grows the KV cache, so it increases the memory needed to run the model.
What is the best quantization for unsloth/Ornith-1.0-35B-GGUF?
For unsloth/Ornith-1.0-35B-GGUF, a strong default is Q4_K_M, which needs about 21.49 GB and keeps most of the quality while roughly halving the memory versus 8-bit. With VRAM to spare, Q5_K_M or Q6_K add a little more quality; if you are tight on memory, a smaller quantization still runs. Pick the highest quantization that fits your VRAM.