0xBakeer/TandemLLM-Flint-EXL3-6.0
text-generation model by 0xBakeer
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
These are EXL3 weights of Recursive's Flint at 6.0 bits per weight, 30.5 GB in all. We converted them from the BF16 checkpoint, RecursiveSI/flint at revision 2a247be0, with exllamav3 1.6.2 and the patch in convert/, which adds the Flint architecture. Every projection is at 6 bits: attention, the two dense layers, the shared experts and the routed experts. The output head is at 8 bits. The router, the norms and the attention sinks stay at 16 bits. This is the quality size. The 4.0 pack decodes about 38 % faster and loses more against BF16. We serve these weights with TandemLLM, our inference engine for one DGX Spark. Flint has 49 layers. Two are dense; the other 47 have 256 routed experts, of which 6 run a token, plus one shared expert. Attention has 32 query heads and 4 KV heads with a learned sink per head. 35 layers use…
Read the full model card ↗ · Preview checked 2026-10-31T11:13:21.216Z
Inside the original model card — Document outline
- Flint in EXL3, 6.0 bits per weight
- One thing loaders need to know
- Quality against BF16
- Speed on a DGX Spark
- Long-context cache (FP8), from TandemLLM 0.14.1 on
- Tool calls: tool-eval-bench, from TandemLLM 0.14.1 on
- How to run it
- How we made it
- License
- Credits
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
0xBakeer/TandemLLM-Flint-EXL3-6.0 is a text-generation model repository published by 0xBakeer on Hugging Face. The source reports the exllamav3 library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- exllamav3
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 15,259,533,728
- Architecture
- FlintForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-22T06:11:08.000Z
- Last modified
- 2026-10-22T06:12:15.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: RecursiveSI/flint
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-22T06:45:03.943Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.