github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15679] Misrepresented parameter_size for gemma4:26b MLX models #35762

New Issue
Open
opened 2026-04-22 20:26:55 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 20:26:55 -05:00
Owner
Copy Link

Originally created by @Archiklein on GitHub (Apr 18, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15679

What is the issue?

Both gemma4:26b-mxfp8 and gemma4:26b-nvfp4 don't seem to be reporting their parameter size correctly. With /api/tags just an empty 'parameter_size' value is being returned, and with /api/show the 'parameter_size' is reported as "8.7B" and "6.3B" respectively.

Even with MLX / safetensors models, shouldn't the parameter size still be "26B" or "26B-A4B" or similar?

Relevant log output

curl http://localhost:11434/api/tags

{
    "models":[
        {
            "name": "gemma4:26b-mxfp8",
            "model": "gemma4:26b-mxfp8",
            "modified_at": "2026-04-18T20:14:14.536292905+02:00",
            "size": 26812605336,
            "digest": "3950c545841fdff310cc84e187ff0538e4a4962fff507e60caf2965cd3749a04",
            "details":{
                "parent_model": "",
                "format": "safetensors",
                "family": "",
                "families": null,
                "parameter_size": "",
                "quantization_level": "mxfp8"
            }
        }
    ]
}


curl http://localhost:11434/api/show -d '{
  "model": "gemma4:26b-mxfp8"  
}'

{
    "license": "Apache License ...",
    "parameters": "temperature 1\ntop_k 64\ntop_p 0.95",
    "template": "{{ .Prompt }}",
    "details": {
        "parent_model": "",
        "format": "safetensors",
        "family": "gemma4",
        "families": null,
        "parameter_size": "8.7B",
        "quantization_level": "mxfp8"
    },
    "model_info":{
        "gemma4.block_count":30,
        "gemma4.context_length":262144,
        "gemma4.embedding_length":2816,
        "general.architecture":"gemma4",
        "general.parameter_count":8677362766
    },
    "capabilities":[
        "completion",
        "tools",
        "thinking"
    ],
    "modified_at":"2026-04-18T20:14:14.536292905+02:00",
    "requires":"0.19.0"
}

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.21.0

Originally created by @Archiklein on GitHub (Apr 18, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15679 ### What is the issue? Both gemma4:26b-mxfp8 and gemma4:26b-nvfp4 don't seem to be reporting their parameter size correctly. With /api/tags just an empty 'parameter_size' value is being returned, and with /api/show the 'parameter_size' is reported as "8.7B" and "6.3B" respectively. Even with MLX / safetensors models, shouldn't the parameter size still be "26B" or "26B-A4B" or similar? ### Relevant log output ```shell curl http://localhost:11434/api/tags { "models":[ { "name": "gemma4:26b-mxfp8", "model": "gemma4:26b-mxfp8", "modified_at": "2026-04-18T20:14:14.536292905+02:00", "size": 26812605336, "digest": "3950c545841fdff310cc84e187ff0538e4a4962fff507e60caf2965cd3749a04", "details":{ "parent_model": "", "format": "safetensors", "family": "", "families": null, "parameter_size": "", "quantization_level": "mxfp8" } } ] } curl http://localhost:11434/api/show -d '{ "model": "gemma4:26b-mxfp8" }' { "license": "Apache License ...", "parameters": "temperature 1\ntop_k 64\ntop_p 0.95", "template": "{{ .Prompt }}", "details": { "parent_model": "", "format": "safetensors", "family": "gemma4", "families": null, "parameter_size": "8.7B", "quantization_level": "mxfp8" }, "model_info":{ "gemma4.block_count":30, "gemma4.context_length":262144, "gemma4.embedding_length":2816, "general.architecture":"gemma4", "general.parameter_count":8677362766 }, "capabilities":[ "completion", "tools", "thinking" ], "modified_at":"2026-04-18T20:14:14.536292905+02:00", "requires":"0.19.0" } ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.21.0
GiteaMirror added the bug label 2026-04-22 20:26:55 -05:00
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 bug
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#35762
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?