JEV 35B needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 18.6 GB (Q3_K_L) to 71.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
JEV 35B – a 35.5B parameter decision model with vision and tools support
JEV 35B is a 35.5B parameter mixture‑of‑experts model based on Qwen3.5-35B-A3B. It is fine‑tuned for decision tasks, supporting reasoning, tools, and vision. The model runs on a single GPU with 32–48 GB VRAM when using NVFP4.
Good at
- Decision making with up to 256 options
- Vision inference with a public score of 71.94
- Reasoning and tool use in a single pass
Limits
- No text generation or chat mode
- Requires 32–48 GB VRAM for NVFP4
- Apache‑2.0 license limits commercial use without attribution
Best for
- Rapid recommendation engines
- News ranking and search re‑ranking
- Embedded decision systems in limited GPU environments
Who it’s for. Developers building decision‑oriented applications that need vision and tool integration. The model is suitable for teams that can run it on a single high‑VRAM GPU and comply with the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 18.6 GB | 19.7 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 26.5 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → | |
| BF16 | 71.1 GB | 72.3 GB | Too big | Get file → |
For 8 GB VRAM use Q3_K_L (18.55 GB file, 19.7 GB memory). For 16 GB VRAM use Q4_K_M (21.71 GB file, 22.9 GB memory). For 32 GB VRAM use Q5_K_M (25.35 GB file, 26.5 GB memory). The BF16 quant requires 71.07 GB file and 72.3 GB memory and is only suitable for 32–48 GB GPUs.
What GPU do you need for JEV 35B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
Which JEV 35B quant should you choose?
Q4_K_M is the usual starting point for JEV 35B: it balances file size and quality well. Here it is a 21.7 GB file.
If memory is tight, the smallest file is Q3_K_L at 18.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about JEV 35B
How much VRAM does JEV 35B need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run JEV 35B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of JEV 35B GGUF?
It depends on the quant: Q3_K_L is 18.6 GB, Q4_K_M is 21.7 GB, Q5_K_M is 25.3 GB, Q6_K is 29.2 GB, BF16 is 71.1 GB.
What context length does JEV 35B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download JEV 35B GGUF?
The files are on Hugging Face in the prithivMLmods/autotrust-JEV-35B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does JEV 35B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run JEV 35B on 8 GB VRAM?
No, the smallest quant Q3_K_L requires 19.7 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does JEV 35B support text generation?
No, it is a decision‑only model with no chat or text generation capability.