EV

Evidence RL 9B

EvidenceGGUF by mradermacherUpdated 2026-09-27
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Evidence RL 9B needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Evidence RL 9B – a vision‑enabled Qwen3.5‑based LLM

Evidence RL 9B is a Qwen/Qwen3.5‑9B derived model trained for evidence‑intensive visual reasoning. It uses Gated GRPO with Counterfactual Evidence Disentanglement to reduce visual hallucinations. The model supports vision tasks and is released under Apache‑2.0.

Good at

  • Vision‑centric reasoning
  • Evidence‑based answer generation
  • Counterfactual region interventions

Limits

  • No text‑only mode; requires vision support
  • Large context size of 262144 tokens
  • Requires GPU with sufficient VRAM for chosen quant

Best for

  • Image‑captioning with evidence grounding
  • Visual question answering with counterfactual checks
  • Research on visual hallucination mitigation

Who it’s for. Developers and researchers needing a vision‑enabled LLM that prioritizes evidence. The model is suitable for applications that require reliable visual reasoning and counterfactual analysis.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S2.7 GB 4.3 GB
Fits Get file →
IQ1_M2.9 GB 4.5 GB
Fits Get file →
IQ2_XXS3.1 GB 4.7 GB
Fits Get file →
IQ2_XS3.3 GB 4.9 GB
Fits Get file →
IQ2_S3.4 GB 5.0 GB
Fits Get file →
IQ2_M3.6 GB 5.2 GB
Fits Get file →
Q2_K_S3.7 GB 5.3 GB
Fits Get file →
Q2_K3.8 GB 5.4 GB
Fits Get file →
IQ3_XXS3.9 GB 5.5 GB
Fits Get file →
IQ3_XS4.2 GB 5.8 GB
Fits Get file →
Q3_K_S4.3 GB 5.8 GB
Fits Get file →
IQ3_S4.4 GB 5.9 GB
Fits Get file →
IQ3_M4.4 GB 6.0 GB
Fits Get file →
Q3_K_M4.6 GB 6.2 GB
Fits Get file →
Q3_K_L4.9 GB 6.5 GB
Fits Get file →
IQ4_XS5.2 GB 6.8 GB
Fits Get file →
Q4_05.3 GB 6.9 GB
Fits Get file →
Q4_K_S5.4 GB 6.9 GB
Fits Get file →
IQ4_NL5.4 GB 7.0 GB
Fits Get file →
Q4_K_M5.6 GB 7.2 GB
Tight Get file →
Q4_15.8 GB 7.4 GB
Tight Get file →
Q5_K_S6.3 GB 7.9 GB
Tight Get file →
Q5_K_M6.5 GB 8.0 GB
Too big Get file →
Q6_K7.4 GB 8.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.74 GB, 4.3 GB memory) or Q2_K (3.83 GB, 5.4 GB memory). For 12 GB VRAM, Q3_K_M (4.62 GB, 6.2 GB memory) or Q4_K_M (5.63 GB, 7.2 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q5_K_M (6.47 GB, 8 GB memory).

What GPU do you need for Evidence RL 9B?

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: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.4 GB file, about 8.9 GB in use).

Which Evidence RL 9B quant should you choose?

Q4_K_M is the usual starting point for Evidence RL 9B: it balances file size and quality well. Here it is a 5.6 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyEvidence
Licenseapache-2.0
Downloads (HF)485
Last updated2026-09-27

Frequently asked questions about Evidence RL 9B

How much VRAM does Evidence RL 9B need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Evidence RL 9B on an 8 GB GPU?

Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Evidence RL 9B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.7 GB, IQ1_M is 2.9 GB, IQ2_XXS is 3.1 GB, IQ2_XS is 3.3 GB, IQ2_S is 3.4 GB and 19 more.

What context length does Evidence RL 9B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Evidence RL 9B GGUF?

The files are on Hugging Face in the mradermacher/Evidence-RL-9B-i1-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 Evidence RL 9B 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 Evidence RL 9B on 8 GB VRAM?

Yes, with IQ1_S or Q2_K quants, which estimate 4.3–5.4 GB memory at 8 k context.

Does the model support text‑only inference?

No, it requires vision support and is not designed for text‑only use.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Evidence-RL-9B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Evidence models

All Evidence →

Other small models

All small models →