Ornith 1.0 9B needs ~8.3 GB VRAM. Intel Arc Pro A60 12GB has 12.0 GB. With Q4_K_M quantization, expect ~27 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
26.7 tok/s
TTFT
7242 ms
Safe context
137K
Memory
8.3 GB / 12.0 GB
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 26.7 tok/s | 3950 ms | 137K |
| Coding | A | Runs well | 26.7 tok/s | 7242 ms | 137K |
| Agentic Coding | A | Runs well | 26.7 tok/s | 10533 ms | 137K |
| Reasoning | A | Runs well | 26.7 tok/s | 8558 ms | 137K |
| RAG | A | Runs well | 26.7 tok/s | 13167 ms | 137K |
Inference speed
Estimated decode speed (tokens/sec) for Ornith 1.0 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~132 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 131.6 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 131.6 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 122.8 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 114.5 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 84.9 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 79.1 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 70.9 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 70.3 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 65.9 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 62.5 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 53.3 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 45.0 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 44.5 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 41.2 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 36.3 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 26.4 | Offloads |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Ornith 1.0 9B (9.399999618530273B params) fits at each quantization level on Intel Arc Pro A60 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q1_0_G128 | 1.125 | 1.4 GB | Very Low | A75 |
Q2_0_G128 | 1.71 | 2.5 GB | Low | A77 |
Q2_K | 2 | 3.7 GB | Low | A78 |
Q3_K_S | 3 | 4.6 GB | Low | A79 |
NVFP4 | 4 | 5.3 GB | Medium | A80 |
Q4_K_M | 4 | 5.7 GB | Medium | A80 |
Q5_K_M | 5 | 6.8 GB | High | A80 |
Q6_KBest for your GPU | 6 | 7.7 GB | High | A80 |
Q8_0 | 8 | 10.1 GB | Very High | F0 |
F16 | 16 | 19.3 GB | Maximum | F0 |
Copy-paste commands to run Ornith 1.0 9B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "deepreinforce-ai/Ornith-1.0-9B" \
--hf-file "Ornith-1.0-9B-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| Ternary Bonsai 27B | 27B | S | 20.4 tok/s | |
 Phi-4-reasoning-plus 14B | 14.7B | B | 12 tok/s | |
 Qwen 3 14B | 14B | A | 14.9 tok/s | |
| 1-bit Bonsai 27B | 27B | S | 41.7 tok/s | |
 Ministral 3 14B | 14B | A | 14.8 tok/s |
Yes, Intel Arc Pro A60 12GB can run Ornith 1.0 9B with a A grade (Runs well). Expected decode speed: 26.7 tok/s.
Ornith 1.0 9B (9.399999618530273B parameters) requires approximately 8.3 GB of memory with Q4_K_M quantization.
The recommended quantization for Ornith 1.0 9B is Q4_K_M, which balances quality and memory efficiency.
On Intel Arc Pro A60 12GB, Ornith 1.0 9B achieves approximately 26.7 tokens per second decode speed with a time-to-first-token of 7242ms using Q4_K_M quantization.
For coding workloads, Ornith 1.0 9B on Intel Arc Pro A60 12GB receives a A grade with 26.7 tok/s and 137K context.
On Intel Arc Pro A60 12GB, Ornith 1.0 9B can safely use up to 137K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.
Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/ornith-1.0-9b-on-arc-pro-a60-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: