Artemis-31B-v1.2-abliterix is an open-weight model from Tony Lai. It has 31.3B parameters and a 262,144-token context. At 16-bit it needs about 75.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Drummer proudly presents... - Gemma 4 31B template, thinking or non-thinking. - Sampler wrangling may be required (or be conservative) Artemis v1.2 landed as the strongest Artemis yet — and, for several testers, the strongest Gemma 4 tune they've used.
Runs On
What it takes to serve Artemis-31B-v1.2-abliterix (31.3B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 62.5 GB | 75.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 31.3 GB | 37.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 15.6 GB | 18.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 23, 2026.
Artemis-31B-v1.2-abliterix on every accelerator the SAVRN Index prices, at every precision
Model Card
Drummer proudly presents... - Gemma 4 31B template, thinking or non-thinking. - Sampler wrangling may be required (or be conservative) Artemis v1.2 landed as the strongest Artemis yet — and, for several testers, the strongest Gemma 4 tune they've used. The recurring themes: - Writing that doesn't feel like G4. Immersive, creative prose with genuinely human-sounding dialogue; multiple testers made it their daily driver, and one got so absorbed in the character they forgot to test darker themes at all. - Reasoning that actually works. The think block pulls the right details and the response stays faithful to it — no cross-card personality bleed at ~32k, scenario adherence holding at 20k…
Excerpt from the card by Tony Lai.
Configuration
- Architecture
- Gemma4ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 60
- Hidden size
- 5,376
- Feed-forward size
- 21,504
- Attention heads
- 32
- Key/value heads
- 16
- Head dimension
- 256
- Vocabulary size
- 262,144
- Sliding window (tokens)
- 1,024
- Model type
- gemma4
Identity and Version
- Repository
- kawattaronin/Artemis-31B-v1.2-abliterix
- Publisher
- Tony Lai
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 31.3B parameters
- Languages
- Not stated by the source
- Revision
- a0af99201e6be01cb031bd7b3c9ec141af6901d4
- First published
- 2026-10-05
- Last updated
- 2026-10-05
Files and Weights
13 files, 62.6 GB in total. The weights are 2 files totalling 62.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00002.safetensors | Weights | 49.9 GB | da783a54112b |
| model-00002-of-00002.safetensors | Weights | 12.6 GB | fa4ddfeb2580 |
| config.json | Configuration | 5.4 KB | — |
| generation_config.json | Configuration | 204 B | — |
| model.safetensors.index.json | Configuration | 120.2 KB | — |
| reproduce/reproduce.json | Configuration | 16.9 KB | — |
| README.md | Documentation | 7.7 KB | — |
| reproduce/README.md | Documentation | 1.5 KB | — |
| chat_template.jinja | Other | 18.7 KB | — |
| reproduce/SHA256SUMS | Other | 198 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | cc8d3a0ce364 |
| tokenizer_config.json | Tokenizer | 3.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 62.5 GB
Released by Tony Lai through its official repository on Hugging Face.
Built From
- Derived from google/gemma-4-31B-it
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 62.5 GB |
| 16-bit | 62.5 GB |
| 8-bit | 31.3 GB |
| 4-bit | 15.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Quantized fromArtemis-31B-v1.2-abliterix-i1-GGUF
- Derived fromArtemis-31B-v1.2-abliterix-i1-GGUF
- Quantized fromArtemis-31B-v1.2-abliterix-GGUF
- Derived fromArtemis-31B-v1.2-abliterix-GGUF
Questions About Artemis-31B-v1.2-abliterix
How much GPU memory does Artemis-31B-v1.2-abliterix need?
About 75.1 GB at 16-bit and 18.8 GB at 4-bit: the weights (31.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Artemis-31B-v1.2-abliterix on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What is Artemis-31B-v1.2-abliterix's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.