VISTA-9B
Where it runs 8K context · ≥ 5 t/s floor
| Setup | Best plan | Memory | Generate |
|---|---|---|---|
| 8 GB GPU + 32 GB RAM | native BF16vLLMGPU streams weights from RAM · 12 GiB in RAM | Fits* | ≤ 2.5 t/s Ceiling |
| 12 GB GPU + 32 GB RAM | native BF16vLLMGPU streams weights from RAM · 8 GiB in RAM | Fits* | ≤ 3.6 t/s Ceiling |
| 16 GB GPU + 64 GB RAM | native BF16vLLMGPU streams weights from RAM · 4 GiB in RAM | Fits* | ≤ 7.8 t/s Ceiling |
| 24 GB GPU + 64 GB RAM | native BF16vLLMFull GPU | Fits* | ≤ 53 t/s Ceiling |
| 32 GB GPU + 128 GB RAM | native BF16vLLMFull GPU | Fits* | ≤ 95 t/s Ceiling |
| 2× 24 GB GPUs + 128 GB RAM | native BF16vLLMFull GPU | Fits* | ≤ 49 t/s Ceiling |
| 96 GB workstation GPU + 256 GB RAM | native BF16vLLMFull GPU | Fits* | ≤ 95 t/s Ceiling |
| Mac, 24 GB | MLX 8-bitMLX-LMUnified memory | Fits* | ~24–25 t/s Estimated |
| Mac, 48 GB | MLX 8-bitMLX-LMUnified memory | Fits* | ~24–25 t/s Estimated |
| Mac, 128 GB | MLX 8-bitMLX-LMUnified memory | Fits* | ~44–53 t/s Estimated |
| Mac, 512 GB | MLX 8-bitMLX-LMUnified memory | Fits* | ~52–76 t/s Estimated |
| DGX Spark 128 GB | native BF16vLLMUnified memory | Fits* | ≤ 14 t/s Ceiling |
| Ryzen AI Max+ 395, 128 GB | native BF16vLLMUnified memory | Fits* | ≤ 14 t/s Ceiling |
| CPU only, 64 GB DDR5-5600 dual channel | Does not fit | ||
Same plan engine as the planner, with its default reserves and RAM. How plans are chosen.
Files exact Hugging Face bytes
| Artifact | Size | Files | Revision | Source |
|---|---|---|---|---|
| MLX 8-bit 8-bit pipenetwork/VISTA-9B-MLX-8bit | 8.86 GiB | 2 | 0095aaa6b0 | HF files |
| MLX 4-bit 4-bit pipenetwork/VISTA-9B-MLX-4bit | 4.69 GiB | 1 | bf406c39a2 | HF files |
| Native safetensors BF16 inclusionAI/VISTA-9B | 17.53 GiB | 1 | a4e30d1aae | HF files |
Not found in the representative quant search (not proven unavailable): GGUF FP16, GGUF Q8_0, GGUF Q5_K_M, GGUF Q4_K_M, EXL3, AWQ, GPTQ. Complete selected file sets; projectors, MTP/draft and lookup files are listed separately and budgeted only by plans that use them. File bytes are not allocated memory.
Quality
No Artificial Analysis evaluation mapped to this checkpoint.
Arena text rating
Unknown
Publisher-reported benchmarks
None extracted from the model card.
AA and Arena describe the hosted model in the stated mode, not each quantized file; scores are never inherited by base, pruned, abliterated or quantized variants and never averaged together.
How to run it
No model-specific recipe in the research. The planner binds the backend’s documented command template (llama.cpp, Ollama, LM Studio, MLX, vLLM) to your plan: open a plan’s details.
Recipes are source examples (settings are the publisher’s or author’s, not measured optima) and were not executed by LocalFit. A downloadable file does not prove your backend build supports the architecture.
Reported speeds 0
No reported measurement yet. Submit one.