Artemis 31B v1.2 Abliterix v2 needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.0 GB to 25.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Artemis 31B v1.2 Abliterix v2 – a 31‑billion‑parameter Gemma‑4 model in GGUF format
Artemis 31B v1.2 Abliterix v2 is a 31‑billion‑parameter Gemma‑4 model. It is available in multiple quantizations for use with llama.cpp. The model supports up to 262,144 context tokens and is designed for text generation and reasoning tasks.
Good at
- High‑quality creative writing
- Accurate reasoning over long contexts
- Consistent dialogue tracking
Limits
- No vision support
- Requires large VRAM for higher‑quality quants
- License terms not specified
Best for
- Long‑form storytelling
- Complex question answering
- Dialogue simulation
Who it’s for. Developers and researchers who need a large Gemma‑4 model for text generation and reasoning. The model is suitable for local deployment with llama.cpp and requires sufficient VRAM for the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 32.7 GB | Too big | Get file → | |
| IQ1_S | 7.2 GB | 39.9 GB | Too big | Get file → | |
| IQ1_M | 7.7 GB | 40.4 GB | Too big | Get file → | |
| IQ2_XXS | 8.7 GB | 41.4 GB | Too big | Get file → | |
| IQ2_XS | 9.5 GB | 42.2 GB | Too big | Get file → | |
| IQ2_S | 10.2 GB | 42.9 GB | Too big | Get file → | |
| IQ2_M | 10.9 GB | 43.6 GB | Too big | Get file → | |
| Q2_K_S | 11.0 GB | 43.7 GB | Too big | Get file → | |
| Q2_K | 11.9 GB | 44.6 GB | Too big | Get file → | |
| IQ3_XXS | 12.1 GB | 44.8 GB | Too big | Get file → | |
| IQ3_XS | 13.1 GB | 45.8 GB | Too big | Get file → | |
| IQ3_S | 13.8 GB | 46.5 GB | Too big | Get file → | |
| Q3_K_S | 13.8 GB | 46.5 GB | Too big | Get file → | |
| IQ3_M | 14.4 GB | 47.1 GB | Too big | Get file → | |
| Q3_K_M | 15.3 GB | 48.0 GB | Too big | Get file → | |
| Q3_K_L | 16.6 GB | 49.3 GB | Too big | Get file → | |
| IQ4_XS | 16.7 GB | 49.4 GB | Too big | Get file → | |
| Q4_0 | 17.7 GB | 50.4 GB | Too big | Get file → | |
| Q4_K_S | 17.8 GB | 50.5 GB | Too big | Get file → | |
| Q4_K_M | 18.7 GB | 51.4 GB | Too big | Get file → | |
| Q4_1 | 19.5 GB | 52.2 GB | Too big | Get file → | |
| Q5_K_S | 21.3 GB | 54.0 GB | Too big | Get file → | |
| Q5_K_M | 21.8 GB | 54.6 GB | Too big | Get file → | |
| Q6_K | 25.2 GB | 57.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (7.16 GB) or Q2_K_S (10.98 GB) if you can spare more memory. For 12 GB VRAM, IQ2_XS (9.53 GB) or Q2_K (11.92 GB) are good choices. Higher‑quality quants such as Q5_K_M (21.85 GB) need at least 22 GB VRAM.
What GPU do you need for Artemis 31B v1.2 Abliterix v2?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q3_K_M (15.3 GB file, about 48.0 GB in use).
Which Artemis 31B v1.2 Abliterix v2 quant should you choose?
Q4_K_M is the usual starting point for Artemis 31B v1.2 Abliterix v2: it balances file size and quality well. Here it is a 18.7 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
Frequently asked questions about Artemis 31B v1.2 Abliterix v2
How much VRAM does Artemis 31B v1.2 Abliterix v2 need?
About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Artemis 31B v1.2 Abliterix v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Artemis 31B v1.2 Abliterix v2 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 7.2 GB, IQ1_M is 7.7 GB, IQ2_XXS is 8.7 GB, IQ2_XS is 9.5 GB, IQ2_S is 10.2 GB and 18 more.
What context length does Artemis 31B v1.2 Abliterix v2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Artemis 31B v1.2 Abliterix v2 GGUF?
The files are on Hugging Face in the mradermacher/Artemis-31B-v1.2-abliterix-v2-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Artemis 31B v1.2 Abliterix v2 on 8 GB VRAM?
Yes, using the IQ1_S quant (7.16 GB) or Q2_K_S (10.98 GB) if you can allocate slightly more memory.
Does this model support vision tasks?
No, Artemis 31B v1.2 Abliterix v2 is a text‑only model; vision files are not included.
What is the maximum context length?
The model was trained with 262,144 context tokens, but practical limits depend on the quant and available VRAM.