Yes — with 8.3 GB to spare
Ornith 1.5 9B at Q4_K_M fits your Tesla P100 16 GB entirely on the GPU at 8K context, at an estimated 84 tokens per second. There is room for its full 256K window.
The small Ornith: a coding-agent reasoning build on the Qwen3.5 9B architecture. Same VRAM as its base, thinks before every answer.
Hardware requirements What hardware do I need to run Ornith 1.5 9B? →At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 17.5 GB | 18.4 GB | — | ~7.1 | Reference | 4.0 GB over |
| Q8_0 | 9.3 GB | 10.2 GB | 143K | 48 | −0.1% ppl | Long context |
| Q6_K | 7.2 GB | 8.0 GB | 211K | 62 | −0.4% ppl | Long context |
| Q5_K_M | 6.2 GB | 7.1 GB | 242K | 71 | −0.8% ppl | Long context |
| Q4_K_M | 5.3 GB | 6.1 GB | 256K | 84 | −1.9% ppl | Recommended |
| Q3_K_M | 4.3 GB | 5.1 GB | 256K | 103 | −5.4% ppl | Long context |
| Q2_K | 3.7 GB | 4.5 GB | 256K | 121 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 8 of its 32 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ ollama pull ornith-1.5:9b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run ornith-1.5:9b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on a Tesla P100 16 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ornith 1.5 35B-A3B 35.9B MoE · same family |
Q4_K_M · 20.9 GB | ~20 | CPU offload |
| Ornith 1.5 397B-A17B 397B MoE · same family |
Q4_K_M · 224.1 GB | — | Won't fit |
| Qwen3.5 9B 9.65B · similar size |
Q4_K_M · 6.3 GB | 82 | Runs great |
| Ministral 3 8B 8.92B · similar size |
Q4_K_M · 6.7 GB | 88 | Runs great |
| Granite 4.1 8B 8.79B · similar size |
Q4_K_M · 6.8 GB | 90 | Runs great |
| LFM2.5 8B-A1B 8.47B MoE · similar size |
Q4_K_M · 5.5 GB | 202 | Runs great |
| Fara 7B 8.29B · similar size |
Q4_K_M · 5.7 GB | 95 | Runs great |
Ornith 1.5 9B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
6.1 GB | 29 | Tight fit |
| Arc B570 8.8 GB usable · 380 GB/s |
6.1 GB | 43 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
6.1 GB | 41 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
6.1 GB | 13 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
6.1 GB | 115 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
6.1 GB | 110 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
6.1 GB | 42 | Runs great |