Run janhq/Jan-v3.5-4B-gguf locally
janhq/Jan-v3.5-4B-gguf is a mid-size language model with 4.41 billion parameters, built on the qwen3 architecture. It is released under the apache-2.0 license and has been downloaded 330,116 times.
To run janhq/Jan-v3.5-4B-gguf locally at a 4,096-token context, its quantized versions need between 3.06 GB (Q3_K_S, lowest quality) and 9.37 GB (GGUF, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is GGUF, needing about 9.37 GB. That means janhq/Jan-v3.5-4B-gguf fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.
All quantizations
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| Q3_K_S | 3.73 | Fair | 1.91 GB | 0.35 GB | 3.06 GB | 209.1 t/s | Fits in VRAM |
| Q3_K_M | 4.07 | Fair | 2.09 GB | 0.35 GB | 3.24 GB | 191.5 t/s | Fits in VRAM |
| Q3_K_L | 4.36 | Good | 2.24 GB | 0.35 GB | 3.39 GB | 178.4 t/s | Fits in VRAM |
| Q4_0 | 4.69 | Good | 2.41 GB | 0.35 GB | 3.56 GB | 165.9 t/s | Fits in VRAM |
| Q4_K_S | 4.72 | Good | 2.42 GB | 0.35 GB | 3.57 GB | 165.1 t/s | Fits in VRAM |
| Q4_K_M | 4.93 | Good | 2.53 GB | 0.35 GB | 3.68 GB | 158.1 t/s | Fits in VRAM |
| Q4_1 | 5.15 | Very good | 2.64 GB | 0.35 GB | 3.8 GB | 151.2 t/s | Fits in VRAM |
| Q4_K_XL | 5.44 | Very good | 2.79 GB | 0.35 GB | 3.94 GB | 143.2 t/s | Fits in VRAM |
| Q5_0 | 5.61 | Very good | 2.88 GB | 0.35 GB | 4.03 GB | 138.9 t/s | Fits in VRAM |
| Q5_K_S | 5.61 | Very good | 2.88 GB | 0.35 GB | 4.03 GB | 138.9 t/s | Fits in VRAM |
| Q5_K_M | 5.72 | Very good | 2.94 GB | 0.35 GB | 4.09 GB | 136.0 t/s | Fits in VRAM |
| Q5_1 | 6.06 | Very good | 3.11 GB | 0.35 GB | 4.26 GB | 128.5 t/s | Fits in VRAM |
| Q6_K | 6.57 | Excellent | 3.38 GB | 0.35 GB | 4.53 GB | 118.5 t/s | Fits in VRAM |
| Q8_0 | 8.51 | Excellent | 4.37 GB | 0.35 GB | 5.52 GB | 91.5 t/s | Fits in VRAM |
| GGUF | 16.01 | Excellent | 8.22 GB | 0.35 GB | 9.37 GB | 48.6 t/s | Fits in VRAM |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
How much VRAM do you need to run janhq/Jan-v3.5-4B-gguf?
You need about 5.52 GB of VRAM to run janhq/Jan-v3.5-4B-gguf entirely on the GPU using the Q8_0 quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run janhq/Jan-v3.5-4B-gguf on an 8 GB GPU?
Yes. With 8 GB of VRAM you can run janhq/Jan-v3.5-4B-gguf fully on the GPU using Q8_0 (about 5.52 GB).
Can I run janhq/Jan-v3.5-4B-gguf on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run janhq/Jan-v3.5-4B-gguf fully on the GPU using GGUF (about 9.37 GB).
Can I run janhq/Jan-v3.5-4B-gguf on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run janhq/Jan-v3.5-4B-gguf fully on the GPU using GGUF (about 9.37 GB).
What is the best quantization for janhq/Jan-v3.5-4B-gguf?
If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.