github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.5k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8752] Mistral Small 3 quants missing #5678

New Issue
Open
opened 2026-04-12 16:58:29 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 16:58:29 -05:00
Owner
Copy Link

Originally created by @Eve-146T on GitHub (Feb 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8752

For mistral small 3 only q4_k_m and q8_0 quants are available, but not q6 q5 etc.

Originally created by @Eve-146T on GitHub (Feb 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8752 For mistral small 3 only q4_k_m and q8_0 quants are available, but not q6 q5 etc.
GiteaMirror added the model label 2026-04-12 16:58:29 -05:00
GiteaMirror commented 2026-04-12 16:58:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 1, 2025):

Until other quants are made available, if you are willing to pull the fp16 quant, you can make your own q6:

$ ollama pull mistral-small:24b-instruct-2501-fp16
$ echo FROM mistral-small:24b-instruct-2501-fp16 > Modelfile
$ ollama create --quantize Q6_K mistral-small:24b-instruct-2501-q6_k

$ ollama show mistral-small:24b-instruct-2501-q6_k
  Model
    architecture        llama    
    parameters          23.6B    
    context length      32768    
    embedding length    5120     
    quantization        Q6_K     

  Parameters
    temperature    0.15    

  System
    You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup           
      headquartered in Paris. Your knowledge base was last updated on 2023-10-01. When you're not sure        
      about some information, you say that you don't have the information and don't make up anything.         
      If the user's question is not clear, ambiguous, or does not provide enough context for you to           
      accurately answer the question, you do not try to answer it right away and you rather ask the user      
      to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or       
      "When is the next flight to Tokyo" => "Where do you travel from?")                                      

  License
    Apache License               
    Version 2.0, January 2004    

$ ollama run mistral-small:24b-instruct-2501-q6_k "why is the sky blue?"
The sky appears blue due to a particular type of scattering called Rayleigh scattering. As light passes through Earth's atmosphere, it collides with gas molecules and tiny particles in the air. Shorter 
wavelengths of light (like blue and violet) are scattered more because they travel in shorter, smaller waves. This is why we perceive the sky as blue most of the time.

Interestingly, violet light is scattered even more than blue light, but the sky appears blue, not violet, because our eyes are more sensitive to blue light and because some of the violet light gets 
absorbed by the atmosphere, shifting the perceived color towards blue.

During sunrise or sunset, the sunlight has to pass through more of Earth's atmosphere, which scatters more of the blue and green light away, and we are left with the warmer colors of sunrise and sunset, 
like reds, oranges, and yellows.
<!-- gh-comment-id:2628992931 --> @rick-github commented on GitHub (Feb 1, 2025): Until other quants are made available, if you are willing to pull the fp16 quant, you can make your own q6: ```console $ ollama pull mistral-small:24b-instruct-2501-fp16 $ echo FROM mistral-small:24b-instruct-2501-fp16 > Modelfile $ ollama create --quantize Q6_K mistral-small:24b-instruct-2501-q6_k $ ollama show mistral-small:24b-instruct-2501-q6_k Model architecture llama parameters 23.6B context length 32768 embedding length 5120 quantization Q6_K Parameters temperature 0.15 System You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris. Your knowledge base was last updated on 2023-10-01. When you're not sure about some information, you say that you don't have the information and don't make up anything. If the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?") License Apache License Version 2.0, January 2004 $ ollama run mistral-small:24b-instruct-2501-q6_k "why is the sky blue?" The sky appears blue due to a particular type of scattering called Rayleigh scattering. As light passes through Earth's atmosphere, it collides with gas molecules and tiny particles in the air. Shorter wavelengths of light (like blue and violet) are scattered more because they travel in shorter, smaller waves. This is why we perceive the sky as blue most of the time. Interestingly, violet light is scattered even more than blue light, but the sky appears blue, not violet, because our eyes are more sensitive to blue light and because some of the violet light gets absorbed by the atmosphere, shifting the perceived color towards blue. During sunrise or sunset, the sunlight has to pass through more of Earth's atmosphere, which scatters more of the blue and green light away, and we are left with the warmer colors of sunrise and sunset, like reds, oranges, and yellows. ```
GiteaMirror commented 2026-04-12 16:58:30 -05:00
Author
Owner
Copy Link

@arbv commented on GitHub (Feb 10, 2025):

Pretty please. My hardware can run better quants than Q4_K_M while Q_8 is too large for me. So, I must stick to Q4_K_M for now which is not good.

I think the situation is similar for a lot of people.

<!-- gh-comment-id:2649144028 --> @arbv commented on GitHub (Feb 10, 2025): Pretty please. My hardware can run better quants than Q4_K_M while Q_8 is too large for me. So, I must stick to Q4_K_M for now which is not good. I think the situation is similar for a lot of people.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label model
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5678
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?