granite vision 4.1 4b
4B parameters · 128k context · Apache 2.0 · released 2026-04-29
vision
In short
granite vision 4.1 4b is an open model from IBM with 4B parameters. At Q4_K_M, granite vision 4.1 4b needs about 3 GB of memory at 8k context and 8 GB at 64k, counting the weights, the KV cache and runtime buffers. The cheapest hardware in Canada that runs granite vision 4.1 4b fully in memory at 64k context is the NVIDIA GeForce RTX 3060 12GB, $497 at Amazon, at about 25 tok/s (estimated).
Updated . Speeds are estimates; how they are worked out.
What to run it on in Canada
Fully in memory at 64k context, priced at retailers today.
Cheapest
NVIDIA GeForce RTX 3060 12GB25tok/sest.Q8_0
$497
Best value
NVIDIA GeForce RTX 3080 10GB60tok/sest.Q5_K_M
$769
Fastest
NVIDIA RTX PRO 6000 Blackwell124tok/sest.Q8_0
$3,133
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File | @8k | @32k | @64k | @128k |
|---|---|---|---|---|---|
| Q4_K_Mgguf | 2.0 GB | 3.3 GB | 5.3 GB | 8.0 GB | 13.4 GB |
| Q5_K_Mgguf | 2.3 GB | 3.6 GB | 5.7 GB | 8.3 GB | 13.7 GB |
| Q8_0gguf | 3.4 GB | 4.7 GB | 6.8 GB | 9.4 GB | 14.8 GB |
Run it
Copy a command for the runtime you use.
- Q4_K_M
- Ollama
ollama run hf.co/ibm-granite/granite-vision-4.1-4b-GGUF:Q4_K_M - LM Studio
lms get ibm-granite/granite-vision-4.1-4b-GGUF@q4_k_m - llama.cpp
llama-server -hf ibm-granite/granite-vision-4.1-4b-GGUF:Q4_K_M
- Ollama
- Q5_K_M
- Ollama
ollama run hf.co/ibm-granite/granite-vision-4.1-4b-GGUF:Q5_K_M - LM Studio
lms get ibm-granite/granite-vision-4.1-4b-GGUF@q5_k_m - llama.cpp
llama-server -hf ibm-granite/granite-vision-4.1-4b-GGUF:Q5_K_M
- Ollama
- Q8_0
- Ollama
ollama run hf.co/ibm-granite/granite-vision-4.1-4b-GGUF:Q8_0 - LM Studio
lms get ibm-granite/granite-vision-4.1-4b-GGUF@q8_0 - llama.cpp
llama-server -hf ibm-granite/granite-vision-4.1-4b-GGUF:Q8_0
- Ollama
Notes
Specialised for chart, table and key-value extraction from documents; may not generalise well to open-ended vision tasks and is English-only. Requires transformers>=5.8.0 (or trust_remote_code on older versions) or vLLM>=0.21.0.
Questions
- How much VRAM does granite vision 4.1 4b need?
- At Q4_K_M, granite vision 4.1 4b needs about 3 GB of memory at 8k context and 8 GB at 64k, counting the weights, the KV cache and runtime buffers.
- What is the best GPU for running granite vision 4.1 4b locally?
- The cheapest hardware in Canada that runs granite vision 4.1 4b fully in memory at 64k context is the NVIDIA GeForce RTX 3060 12GB, $497 at Amazon, at about 25 tok/s (estimated). The best value is the NVIDIA GeForce RTX 3080 10GB (about 60 tok/s for $769). The fastest we price is the NVIDIA RTX PRO 6000 Blackwell, at about 124 tok/s.
- Can I run granite vision 4.1 4b on a 16 GB GPU?
- Yes: at Q8_0 it fits fully in 16 GB at 64k context. On the NVIDIA GeForce RTX 5080 it runs at about 66 tok/s (estimated).
- Can I run granite vision 4.1 4b on a 24 GB GPU?
- Yes: at Q8_0 it fits fully in 24 GB at 64k context. On the NVIDIA GeForce RTX 3090 Ti it runs at about 70 tok/s (estimated).
- How do I run granite vision 4.1 4b locally?
- With Ollama: ollama run hf.co/ibm-granite/granite-vision-4.1-4b-GGUF:Q4_K_M (the Q4_K_M build). LM Studio and llama.cpp commands are on this page.
- What licence is granite vision 4.1 4b released under?
- Apache 2.0, which allows commercial use.