---

license: cc-by-sa-4.0

base_model: kyutai/helium-1-2b

tags:

• kyutai
• helium
• llama
• base-model
• multilingual
• edge
• mobile
• europe
• gguf
• llama.cpp
• 12gb-gpu
• 8gb-gpu
• 6gb-gpu
• ollama
• lm-studio
• q2_k
• q3_k_m
• q4_k_m
• q5_k_m
• q6_k
• q8_0
• 4gb
• cpu
• laptop

language:

• bg
• cs
• da
• de
• el
• en
• es
• et
• fi
• fr
• ga
• hr
• hu
• it
• lt
• lv
• mt
• nl
• pl
• pt
• ro
• sk
• sl
• sv

pipeline_tag: text-generation

library_name: gguf

base_model_relation: quantized

---

Helium-1-2B — GGUF

> 🟢 Fits on: every GPU class — even integrated graphics. Runs on phones at Q2_K.

GGUF conversion of kyutai/helium-1-2b — Kyutai's lightweight 2B base language model targeting edge and mobile devices, with native support for all 24 official EU languages.

This is a community quantization. The base model is by Kyutai (creators of Mimi, Moshi, and the Kyutai TTS/STT family). Until now, only MLX (Apple Silicon) variants existed — this fills the GGUF gap for llama.cpp and ollama users.

Model details

| Field | Value |

|---|---|

| Architecture | LlamaForCausalLM (standard Llama; works with stock llama.cpp) |

| Parameters | 2B |

| Layers | 28 |

| Hidden size | 2048 |

| Vocab | 64,000 (multilingual) |

| Context | 4K |

| Type | Base model — not instruction-tuned |

| License | CC-BY-SA 4.0 + Gemma Terms of Use (Helium is distilled from Gemma 2) |

Use case

• Edge / mobile inference — fits comfortably on consumer hardware, including phones and small GPUs
• EU multilingual base — train your own instruction-following model on top of this with the language coverage you need
• Research — distillation lineage from Gemma 2 with smaller footprint
• Not for chat out-of-the-box — this is a base model, no instruction tuning. For chat, fine-tune it first.

Quants

| Quant | Size | Use case |

|---|---|---|

| Q2_K | ~0.8 GB | tiniest footprint — phones, microcontrollers, 4 GB cards |

| Q3_K_M | ~1.0 GB | balance for 6 GB cards |

| Q4_K_M | ~1.2 GB | recommended default — fits anywhere |

| Q5_K_M | ~1.5 GB | quality bump if you have headroom |

| Q6_K | ~1.8 GB | near-lossless |

| Q8_0 | ~2.3 GB | reference quality |

| F16 | ~4.0 GB | full precision |

Usage — Ollama

hf download Hob-forge/helium-1-2b-GGUF \
  helium-1-2b.Q4_K_M.gguf Modelfile --local-dir ./helium
cd ./helium
ollama create helium-1-2b:Q4_K_M -f Modelfile
ollama run helium-1-2b:Q4_K_M "Once upon a time"

Usage — llama.cpp

./build/bin/llama-completion \
    -m helium-1-2b.Q4_K_M.gguf \
    -p "The capital of France is" \
    -n 30 --temp 0.6

(Sample: "The capital of France is Paris...")

License notes

• This conversion is CC-BY-SA 4.0 (matching the source release).
• Helium-1 is distilled from Gemma 2, so use is also subject to the Gemma Terms of Use.
• This GGUF inherits both terms.

Conversion details

• Source: kyutai/helium-1-2b (downloaded 2026-04-29; Q2_K + Q3_K_M backfilled 2026-05-02)
• Tools: stock llama.cpp (no patches required — standard Llama arch)
• Steps: convert_hf_to_gguf.py → llama-quantize

More from Hob-forge

We're a small AI lab making powerful models actually run on consumer GPUs. Curated GGUFs with the full Q2/Q3/Q4 ladder for 12-16 GB cards and first-mover conversions for new architectures.

• Cosmos-Reason2-32B — NVIDIA's reasoning VLM
• Nemotron-3-Nano-Omni-30B — Mamba2-Transformer hybrid MoE
• BAR-5x7B / BAR-2x7B-Tool-Use — AllenAI FlexOlmo
• gpt-oss-20b-Q2_K — 12 GB-VRAM specific cut

→ Full catalogue at huggingface.co/Hob-forge

Acknowledgments

• Kyutai for the open release of Helium-1, targeting under-served EU language coverage at edge scale
• Google DeepMind for the Gemma 2 base from which Helium was distilled
• llama.cpp maintainers