Models / Ornith-1.5-9B

Ornith-1.5-9B

consumer
HuggingFace → HuggingBay → Ornith AI → Find for my hardware

~9B Dense - the edge-deployable Ornith-1.5, released 2026-08-18. Compact enough for phones (a quantized Ornith-1.5-9B-Mobile variant targets iOS/Android) yet matches or exceeds much larger models like Gemma 4-31B and Qwen 3.6-35B on agentic coding. 262K context, MIT-licensed on HuggingFace at ornith-ai/Ornith-1.5-9B (GGUF and MLX quantizations).

  • Coding (vendor self-reported): Terminal-Bench 2.1 46.2, SWE-bench Verified 70.6, SWE-bench Pro 47.5, NL2Repo 32.4.
  • Reasoning: HLE 20.2 (no tools) / 30.5 (with tools), GPQA-Diamond 86.4.
  • Agentic: MCP-Atlas 54.2, Toolathlon-Verified 41.2, ClawEval 66.5.

Runs almost anywhere. Quantized builds run on phones, laptops, and small GPUs; the strongest open-weight coding model at this size. Vendor benchmarks are claims pending independent replication.

coding reasoning agentic
Parameters
9.0B
Context
262k
License
mit
Developer
Ornith AI
Origin
🇺🇸 USA
Released
Aug 2026

Benchmark scores

Vendor-reported - from the developer's own model card / tech report

GPQA-Diamond
86.4
HLE
20.2
MCP-Atlas
54.2
NL2Repo-Bench
32.4
SWE-bench Pro
47.5
SWE-bench Verified
70.6
Terminal-Bench 2.1
46.2
Toolathlon Verified
41.2

Vendor-reported - from the developer's own model card / tech report

Ran this model on your own hardware? Join free and add your measured tok/s to the community numbers.

Related models

Ornith-1.5-35B-A3B
36.0B 3.0B active enthusiast 22GB min RAM Aug 18, 2026
Ornith-1.5-397B
403.0B workstation 248GB min RAM Aug 18, 2026
Ornith-1.0-35B superseded
35.0B 3.0B active enthusiast no local build Jun 25, 2026
Ornith-1.0-397B superseded
397.0B workstation no local build Jun 25, 2026
Ornith-1.0-9B superseded by this
9.0B consumer no local build Jun 25, 2026

Save your hardware and every model page answers the real question: will it run on your machine, and how fast?

Join free - save your rig →

Run it locally

Per-quant memory needs and a static "can you run it?" reference - no rig entry required

Q4_K_M
5.8GB 6.0GB min 8.0GB rec
Balanced - the usual local sweet spot
Q5_K_M
6.6GB 7.0GB min 9.0GB rec
High quality, larger than Q4
Q6_K
7.6GB 8.0GB min 10.0GB rec
Near-lossless, large
Q8_0
9.8GB 10.0GB min 12.0GB rec
Near-lossless
BF16
18.4GB 19.0GB min 22.0GB rec
Full quality, largest

The reference hardware

Schematic of the 4x H100 80GB (320GB) reference rig - 320GB VRAM, 13400 GB/s aggregate bandwidth
Schematic of the NVIDIA DGX Station 748GB reference rig - 748GB unified memory, 8000 GB/s aggregate bandwidth
Schematic of the 8x RTX 3090 rack (192GB) reference rig - 192GB VRAM, 7489 GB/s aggregate bandwidth
Schematic of the 4x RTX 5090 (128GB) reference rig - 128GB VRAM, 7168 GB/s aggregate bandwidth
Schematic of the AMD Instinct MI300X (192GB) reference rig - 192GB VRAM, 5324 GB/s aggregate bandwidth
Schematic of the 4x RTX 4090 (96GB) reference rig - 96GB VRAM, 4032 GB/s aggregate bandwidth
Schematic of the 2x RTX 5090 (64GB) reference rig - 64GB VRAM, 3584 GB/s aggregate bandwidth
Schematic of the 2x RTX 3090 (48GB) reference rig - 48GB VRAM, 1872 GB/s aggregate bandwidth
Schematic of the Single RTX 5090 (32GB) reference rig - 32GB VRAM, 1792 GB/s aggregate bandwidth
Schematic of the RTX PRO 6000 Blackwell (96GB) reference rig - 96GB VRAM, 1792 GB/s aggregate bandwidth
Schematic of the Mac Studio M4 Ultra 192GB reference rig - 192GB unified memory, 1092 GB/s aggregate bandwidth
Schematic of the Mac Studio M4 Ultra 512GB reference rig - 512GB unified memory, 1092 GB/s aggregate bandwidth
Schematic of the Single RTX 4090 (24GB) reference rig - 24GB VRAM, 1008 GB/s aggregate bandwidth
Schematic of the MacBook Pro M5 Max 128GB reference rig - 128GB unified memory, 614 GB/s aggregate bandwidth
Schematic of the Single GTX 1080 Ti (11GB) reference rig - 11GB VRAM, 484 GB/s aggregate bandwidth
Schematic of the Dual EPYC 9004 + 768GB DDR5-4800 reference rig - 768GB unified memory, 460 GB/s aggregate bandwidth
Schematic of the DGX Spark 128GB unified reference rig - 128GB unified memory, 273 GB/s aggregate bandwidth
Schematic of the Ryzen AI Max+ 395 128GB reference rig - 128GB unified memory, 256 GB/s aggregate bandwidth
Schematic of the Jetson AGX Orin 64GB reference rig - 64GB unified memory, 204 GB/s aggregate bandwidth
Schematic of the Epyc + 512GB DDR4-3200 + 2x RTX 3090 reference rig - 560GB unified memory, 204 GB/s aggregate bandwidth
Schematic of the Epyc + 512GB DDR4-2400 + 2x RTX 3090 reference rig - 560GB unified memory, 153 GB/s aggregate bandwidth
Schematic of the NVIDIA Jetson Orin NX 16GB reference rig - 16GB unified memory, 102 GB/s aggregate bandwidth

22 reference configs, drawn in-house. Scroll for more.

Can you run it? - reference rigs

Rig Q4_K_M Q5_K_M Q6_K Q8_0 BF16
4x H100 80GB (320GB) fast 1274.7t/s fast 1109.6t/s fast 974.6t/s fast 752.7t/s fast 400.5t/s
NVIDIA DGX Station 748GB fast 761.0t/s fast 662.5t/s fast 581.9t/s fast 449.4t/s fast 239.1t/s
8x RTX 3090 rack (192GB) fast 712.4t/s fast 620.2t/s fast 544.7t/s fast 420.7t/s fast 223.9t/s
4x RTX 5090 (128GB) fast 681.8t/s fast 593.6t/s fast 521.3t/s fast 402.6t/s fast 214.2t/s
AMD Instinct MI300X (192GB) fast 506.5t/s fast 440.9t/s fast 387.3t/s fast 299.1t/s fast 159.2t/s
4x RTX 4090 (96GB) fast 383.5t/s fast 333.9t/s fast 293.3t/s fast 226.5t/s fast 120.5t/s
2x RTX 5090 (64GB) fast 340.9t/s fast 296.8t/s fast 260.7t/s fast 201.3t/s fast 107.1t/s
2x RTX 3090 (48GB) fast 178.1t/s fast 155.1t/s fast 136.2t/s fast 105.2t/s fast 56.0t/s
Single RTX 5090 (32GB) fast 170.5t/s fast 148.4t/s fast 130.3t/s fast 100.7t/s fast 53.6t/s
RTX PRO 6000 Blackwell (96GB) fast 170.5t/s fast 148.4t/s fast 130.3t/s fast 100.7t/s fast 53.6t/s
Mac Studio M4 Ultra 192GB fast 113.3t/s fast 98.6t/s fast 86.6t/s fast 66.9t/s fast 35.6t/s
Mac Studio M4 Ultra 512GB fast 113.3t/s fast 98.6t/s fast 86.6t/s fast 66.9t/s fast 35.6t/s
Single RTX 4090 (24GB) fast 95.9t/s fast 83.5t/s fast 73.3t/s fast 56.6t/s fast 30.1t/s
MacBook Pro M5 Max 128GB fast 63.7t/s fast 55.5t/s fast 48.7t/s fast 37.6t/s fast 20.0t/s
Single GTX 1080 Ti (11GB) fast 46.0t/s fast 40.1t/s fast 35.2t/s tight no -> cloud
Dual EPYC 9004 + 768GB DDR5-4800 fast 43.8t/s fast 38.2t/s fast 33.5t/s fast 25.9t/s ok 13.8t/s
DGX Spark 128GB unified fast 26.0t/s fast 22.6t/s ok 19.9t/s ok 15.3t/s ok 8.2t/s
Ryzen AI Max+ 395 128GB fast 24.4t/s fast 21.2t/s ok 18.6t/s ok 14.4t/s slow 7.7t/s
Jetson AGX Orin 64GB ok 19.5t/s ok 17.0t/s ok 14.9t/s ok 11.5t/s slow 6.1t/s
Epyc + 512GB DDR4-3200 + 2x RTX 3090 ok 19.5t/s ok 17.0t/s ok 14.9t/s ok 11.5t/s slow 6.1t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090 ok 14.6t/s ok 12.7t/s ok 11.2t/s ok 8.6t/s slow 4.6t/s
NVIDIA Jetson Orin NX 16GB ok 9.7t/s ok 8.5t/s slow 7.5t/s slow 5.8t/s no -> cloud

Fit tiers use the same will-it-run logic as the rig finder. For comfortable fits, the badge reflects decode speed: fast >=20 t/s, ok 8-20 t/s, slow <8 t/s. t/s is a bandwidth estimate, not a measured benchmark.

Download options

Q4_K_M official -5% vs fp16
5.8GB dl 6.0GB min 8.0GB rec
REC RAM vs largest quant
5.78GB Q4_K_M weights + overhead + KV cache; ~6GB to run in RAM
GGUF on HF →
Q5_K_M official -3% vs fp16
6.6GB dl 7.0GB min 9.0GB rec
REC RAM vs largest quant
GGUF on HF →
Q6_K official -1% vs fp16
7.6GB dl 8.0GB min 10.0GB rec
REC RAM vs largest quant
GGUF on HF →
Q8_0 official -1% vs fp16
9.8GB dl 10.0GB min 12.0GB rec
REC RAM vs largest quant
GGUF on HF →
BF16 official
18.4GB dl 19.0GB min 22.0GB rec
REC RAM vs largest quant
GGUF on HF →

Or run it in the cloud

No per-token API provider pricing tracked for Ornith-1.5-9B yet. For flagship list prices, see the calculator.

PRICE HISTORY

Inference cost over time

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

Loading price history...