localLLMrig
Menu

model

Ornith-1.5-122B: how much memory, and what runs it

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-1.5-122B needs about 76.8 GB at Q4_K_M with 8K context (estimate). See which GPUs and Macs fit it, and EU prices. Speed is not estimated for this mixture-of-experts model.

Licence

Commercial use: yes

Commercial use allowed. Keep the licence and copyright notice when you share the weights.

Licence: MIT · checked 20 Oct 2026

Our reading of the licence, not legal advice.

QuantisationEstimated memory
Q476.8 GBestimate
Q589.8 GBestimate
Q8134.8 GBestimate
FP16251.2 GBestimate

At 8,192 tokens of context. Catalog quant rates are a formula. sourceUrl on that memory stays null.

Parameter count source: huggingface.co/ornith-ai/Ornith-1.5-122B. Marked estimated because the published count is rounded.

VRAM per quant and the cheapest rig for Ornith-1.5-122B

Open in the calculator

Three setups

Ornith-1.5-122B · Q4 · 8,192 ctx

Estimated memory

76.8 GBestimate

75.8 GB weights · 0.2 GB KV cache · 0.8 GB overhead

  1. 01 · Fastest

    Mac Studio M5 Ultra 256GB

    The machine in this list that can still hold 70B in FP16. The euro amount is an estimate.

    $13,994€12,500

    price as of 16 Oct 2026

    price unverified

    Estimate from the 16 Oct 2026 fact-check. Not a checked Apple Store listing. About €12,500–€13,000. This row stores the low end. 256 GB requires the 36-core CPU / 80-core GPU chip.

    speed

    not estimated for MoE yet

    speed: not estimated for MoE yet

    needed

    76.8 GB

    full fit

    usable

    192.0 GB

    unified

    Why this one

    • The model fits entirely in VRAM or unified memory. No CPU offload.
    • Memory left for a longer context or a heavier quantisation.
    • Unified memory: weights and KV cache share one pool.
    • High memory bandwidth, so a higher tokens-per-second estimate.
    • One box, little noise, no discrete GPU.
    • Highest estimated speed in this shortlist.

    Parts

    • Mac Studio M5 Ultra, 256 GB unified memory, 1.2 TB/s
    • 256 GB requires the 36-core CPU / 80-core GPU chip

  2. 02 · Best value

    Mac Studio M4 Max 128GB

    70B Q4 and Q5 fit, Q8 often does too. Slower than a dual 3090, much quieter.

    $3,683€3,290

    price as of 16 Oct 2026

    price unverified

    Used-market euro amount from the earlier catalog. It cannot be checked on the Apple Store.

    used

    speed

    not estimated for MoE yet

    speed: not estimated for MoE yet

    needed

    76.8 GB

    full fit

    usable

    96.0 GB

    unified

    Why this one

    • The model fits entirely in VRAM or unified memory. No CPU offload.
    • Memory left for a longer context or a heavier quantisation.
    • Unified memory: weights and KV cache share one pool.
    • Second-hand or a previous generation. The price moves around.
    • One box, little noise, no discrete GPU.
    • Most estimated tokens per euro in this shortlist.

    Parts

    • Mac Studio (2025) M4 Max 16-core/40-core, 128 GB
    • 546 GB/s according to Apple Support

  3. 03 · A step up

    Mac Studio M5 Max 128GB

    70B up to Q8 has room here. Bandwidth still trails a dual high-end GPU.

    $6,717€6,000

    price as of 16 Oct 2026

    price unverified

    Estimate from the 16 Oct 2026 fact-check. Not a checked Apple Store listing. About €6,000.

    speed

    not estimated for MoE yet

    speed: not estimated for MoE yet

    needed

    76.8 GB

    full fit

    usable

    96.0 GB

    unified

    Why this one

    • The model fits entirely in VRAM or unified memory. No CPU offload.
    • Memory left for a longer context or a heavier quantisation.
    • Unified memory: weights and KV cache share one pool.
    • One box, little noise, no discrete GPU.

    Parts

    • Mac Studio M5 Max 18-core/40-core GPU, 128 GB, 614 GB/s

With CPU offload, and therefore slower, this could also work: Dual RTX 4090, 48 GB, speed: not estimated for MoE yet, $8,206€7,330.

Tokens per second are estimated from memory bandwidth, not from a measured benchmark. Prices incl. VAT, excl. shipping. USD = FX estimate, excl. sales tax. A price without a checked listing is marked price unverified. Run llama-bench yourself before you buy.

Want a build tailored to you? Custom report

Get new builds when GPU prices move

End of results

Embed this

[![Ornith-1.5-122B Q4 on RTX 3060 12GB: ✗ · needs 76.8 GB (estimate)](https://localllmrig.com/badge/ornith-1.5-122b/rtx-3060-12gb.svg)](https://localllmrig.com/can-i-run/ornith-1.5-122b/rtx-3060-12gb?utm_source=badge)

Model badge

[![Ornith-1.5-122B Q4: needs ~76.8 GB VRAM (estimate)](https://localllmrig.com/badge/ornith-1.5-122b.svg)](https://localllmrig.com/models/ornith-1.5-122b?utm_source=badge)

Common questions

How much memory does Ornith-1.5-122B need at Q4?
About 76.8 GB at 8,192 tokens: 75.8 GB weights, 0.2 GB KV cache, 0.8 GB overhead. That is an estimate. sourceUrl stays null.
Does Ornith-1.5-122B fit on a single 24 GB GPU?
Not in full. The estimate is 76.8 GB, and a 24 GB card leaves 23.4 GB usable. sourceUrl stays null.
Are the tokens per second measured?
speed: not estimated for MoE yet