Leanstral-1.5-119B-A6B — BF16 (HF transformers format)
An unofficial, community conversion of
mistralai/Leanstral-1.5-119B-A6B
from Mistral's native (consolidated FP8) format into standard Hugging Face
transformers format, dequantized to BF16. The upstream repo ships only in
Mistral-native format (no config.json), so it cannot be loaded by
AutoModel.from_pretrained. This repo makes it transformers-loadable, which
also unblocks quantization toolchains (llm-compressor, etc.).
Architecture
Composed Mistral3
= DeepSeek-V3 text backbone (MLA + shared-expert MoE: 128 routed experts,
4 active/token, 1 shared) + Pixtral vision. Built by mapping native tensors →
HF names, fusing per-expert weights into the fused MoE layout, and dequantizing
FP8→BF16.
✅ Verified / ⚠️ Not yet verified (tested 2026-07-04 on 1× B200, CUDA 13)
- ✅ Structurally exact: strict key+shape match (801 tensors) against a real
Mistral3(deepseek_v3+pixtral); loads cleanly intransformers. - ⚠️ End-to-end generation on a single B200 not confirmed: BF16 is ~238 GB, larger than one B200's 183 GB VRAM, so it needs multi-GPU (the base model uses tensor-parallel 4) or CPU offload. Short-context generation via device-map offload is functional but slow.
- ⚠️ Vision converted (Pixtral tensors +
preprocessor_config.json) but not runtime-validated. - ⚠️ RoPE approximate: source carries both
yarnandllama_4_scaling; only YARN is mapped. Long-context (>8k) not guaranteed. Short context unaffected.
Provenance & precision
FP8 e4m3 (per-tensor scale) → BF16 (lossless upcast). Note these weights were
already 8-bit in the source, not full-precision training weights.
Intended usage (mirrors the base model)
Tokenizer is Tekken (tekken.json, via mistral_common); Mistral instruct
chat format (no manual [INST]); base recommends temperature 1.0,
reasoning-parser mistral, context ≤ 200k. Example:
vllm serve sahilchachra/Leanstral-1.5-119B-A6B-BF16 \
--tokenizer-mode mistral --tensor-parallel-size 4 \
--reasoning-parser mistral --tool-call-parser mistral --enable-auto-tool-choice
For lower memory / single-GPU, prefer the NVFP4 build:
sahilchachra/Leanstral-1.5-119B-A6B-NVFP4.
Files: config.json, weights + index, tekken.json, params.json,
chat_template.jinja.
License
Derives from mistralai/Leanstral-1.5-119B-A6B; upstream license/terms apply.
Community conversion, not affiliated with Mistral AI.