estimate, except measured file sizes

Can I run Ornith-1.5-122B locally?

125.09B parameters. Parameter count is the published figure.

Licence:

MIT source

Context:

262,144 tokens

Modality:

text + image/video in, text out

Released:

Oct 2026 source

What it is

Ornith's open-weight mixture-of-experts vision-language model, MIT (card frontmatter license: mit; LICENSE at https://huggingface.co/ornith-ai/Ornith-1.5-122B/blob/main/LICENSE). The download is not gated. The card says "122B MOE". Hugging Face safetensors metadata lists 125,086,497,008 parameters, all BF16. 125.09B is that count to two decimals, so this row stores 125.09 and paramsEstimated is false. The card does not state how many parameters are active. Community posts that say about 10B active are unverified and are not stored. Config: Qwen3_5MoeForConditionalGeneration, model_type qwen3_5_moe. 48 layers, 12 full_attention and 36 linear_attention (full_attention_interval 4), so the full-attention share is 12/48. Hidden size 3072. 32 attention heads, 2 KV heads, head dim 256, vocab 248,320. 256 experts, 8 routed per token, moe intermediate size 1024, shared expert intermediate size 1024. Linear-attention layers are stored with a sliding window of 0 so this formula gives them no token KV. The KV figure uses only the 12 full-attention layers and is an FP16 estimate. Config max_position_embeddings is 262,144. The card says YaRN with a scaling factor of 4 grows that window to roughly 1M tokens; this catalog uses 262,144. Text, image and video in, text out. The card's example reads a <think> trace from reasoning_content. Public launch 20 Oct 2026: https://x.com/ornith_/status/2112553477457268799. Hugging Face lists the repo as created on 16 Oct 2026. Speed is not estimated: the formula streams every weight and understates sparse MoE, and no speed figure is stored. Official GGUF sizes, decimal GB, Hugging Face tree 20 Oct 2026, mmproj excluded (https://huggingface.co/ornith-ai/Ornith-1.5-122B-GGUF): Q4_K_M 75.84 (75,843,911,648 bytes), Q5_K_M 88.71, Q6_K 102.38, Q8_0 132.56. Unsloth GGUF, shards summed the same day (https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF): UD-IQ1_M 40.36, UD-IQ2_XXS 41.97, UD-Q2_K_XL 44.53, UD-IQ3_XXS 49.52, UD-Q3_K_XL 59.76, UD-Q4_K_XL 79.71, UD-Q5_K_XL 94.61, UD-Q6_K_XL 114.22. The bits column is the quant name's nominal width, not a measured bits-per-weight. Official BF16 GGUF is 249.36 GB (249,362,980,832 bytes) and is not a memory-table row. mmproj-Ornith-1.5-122B-BF16.gguf is 0.91 GB (912,263,200 bytes) and is not in the table. Community mixed quants, not rows in this table: AtomicChat AD-IQ2_XXS-IQ1_M 34.96 GB and AD-IQ3_XXS-IQ2_S 47.64 GB (https://huggingface.co/AtomicChat/Ornith-1.5-122B-GGUF). Ollama, checked 20 Oct 2026 (https://ollama.com/library/ornith-1.5/tags): ornith-1.5:122b is listed as 73GB–77GB, ornith-1.5:122b-nvfp4 as 73GB, and ornith-1.5:122b-q4_K_M as 77GB.

Ornith-reported

Ornith-reported (model card, not a measurement on this site). The card says Ornith-1.5-122B serves on a single 80GB GPU and runs on a single DGX, and its table lists SWE-bench Verified (non-hack) at 84.5. Source: https://huggingface.co/ornith-ai/Ornith-1.5-122B

Parameter source · Architecture source · Model page

speed: not estimated for MoE yet

Memory per quant

KV is at 8,192 tokens. Overhead is 0.8 GB. Both are estimates. A measured file size is labelled. The last column is the cheapest machine that fits the total fully.

Cheapest rig that fits

Q4_K_M, full: Mac Studio M4 Max 128GB, €3,290 (estimate)

Q4_K_M, slow, partly in system RAM: Used PC with RTX 3090 24GB, slow, partly in system RAM, €2,324 (estimate)

UD-IQ1_M (smallest file), full: Mac mini M4 Pro 64GB, €1,890 (estimate)

UD-IQ1_M (smallest file), slow, partly in system RAM: Budget PC with RTX 3060 12GB, slow, partly in system RAM, €1,357 (estimate)

Prices moved: see Building a local LLM rig in the RAMageddon.

On a specific GPU

• Ornith-1.5-122B on RTX 3060 12GB
• Ornith-1.5-122B on RTX 4060 Ti 16GB
• Ornith-1.5-122B on RTX 3090
• Ornith-1.5-122B on RTX 4090
• Ornith-1.5-122B on RTX 5080
• Ornith-1.5-122B on RTX 5090
• Ornith-1.5-122B on RX 7900 XTX
• Ornith-1.5-122B on Dual RTX 3090
• Ornith-1.5-122B on Dual RTX 4090