Artemis-v1.2-4.00bpw-h6-exl3 is an open-weight model from MikeRoz. It has 9.5B parameters and a 262,144-token context. At 16-bit it needs about 22.8 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
exllamav3 quantizations of TheDrummer's Artemis-31B-v1.2. Quantized using 12414d0 of the dev branch. Requires exllamav3-v1.5.1 or above. 2.25bpwh6 11.761 GiB 4.00bpwh6 17.730 GiB (this model) 6.00bpwh8 24.877 GiB Original model card follows below.
Runs On
What it takes to serve Artemis-v1.2-4.00bpw-h6-exl3 (9.5B 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 | 19.0 GB | 22.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 9.5 GB | 11.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.8 GB | 5.7 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 24, 2026.
Artemis-v1.2-4.00bpw-h6-exl3 on every accelerator the SAVRN Index prices, at every precision
Model Card
exllamav3 quantizations of TheDrummer's Artemis-31B-v1.2. Quantized using 12414d0 of the dev branch. Requires exllamav3-v1.5.1 or above. 2.25bpwh6 11.761 GiB 4.00bpwh6 17.730 GiB (this model) 6.00bpwh8 24.877 GiB Original model card follows below. Model Card WIP - Gemma 4 31B template, thinking or non-thinking. - Sampler wrangling may be required (or be conservative) config-v1q
Excerpt from the card by MikeRoz.
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
- Quantization
- exl3
Identity and Version
- Repository
- MikeRoz/Artemis-v1.2-4.00bpw-h6-exl3
- Publisher
- MikeRoz
- Task
- Not stated by the source
- Modality
- Other
- Library
- exllamav3
- Parameters
- 9.5B parameters
- Languages
- Not stated by the source
- Revision
- 12144a307d110139c68cec201367858fbf475fdc
- First published
- 2026-09-27
- Last updated
- 2026-09-27
Files and Weights
13 files, 19.0 GB in total. The weights are 3 files totalling 19.0 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00003.safetensors | Weights | 8.4 GB | 79c462d57b8a |
| model-00002-of-00003.safetensors | Weights | 8.6 GB | fb81980fd66c |
| model-00003-of-00003.safetensors | Weights | 2.0 GB | ca70107f2d40 |
| config.json | Configuration | 5.7 KB | — |
| generation_config.json | Configuration | 208 B | — |
| model.safetensors.index.json | Configuration | 309.0 KB | — |
| processor_config.json | Configuration | 1.7 KB | — |
| quantization_config.json | Configuration | 664.0 KB | — |
| README.md | Documentation | 1.0 KB | — |
| chat_template.jinja | Other | 18.7 KB | — |
| .gitattributes | Repository | 1.7 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | cc8d3a0ce364 |
| tokenizer_config.json | Tokenizer | 3.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 19.0 GB
Released by MikeRoz through its official repository on Hugging Face.
Built From
- Derived from TheDrummer/Artemis-31B-v1.2
- Quantized from TheDrummer/Artemis-31B-v1.2
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 19.0 GB |
| 16-bit | 19.0 GB |
| 8-bit | 9.5 GB |
| 4-bit | 4.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Artemis-v1.2-4.00bpw-h6-exl3
How much GPU memory does Artemis-v1.2-4.00bpw-h6-exl3 need?
About 22.8 GB at 16-bit and 5.7 GB at 4-bit: the weights (9.5B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Artemis-v1.2-4.00bpw-h6-exl3 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-v1.2-4.00bpw-h6-exl3's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.