Skip to content
localllm
日本語

sbtom

karakuri-midrose-CV

Parameters
69.2B
Max context length
4,096
Architecture
llama
Base model
sbtom/karakuri-midrose-CV

About karakuri-midrose-CV

karakuri-midrose-CV is a GGUF model based on sbtom/karakuri-midrose-CV on Hugging Face. GGUF files are published by mradermacher/karakuri-midrose-CV-GGUF. It has about 69.2B parameters, the llama architecture, a maximum context length of 4,096 tokens (values written in the GGUF).

There are 9 quantizations, with file sizes from 25.6 GB (Q2_K) to 48.9 GB (Q5_K_M) (actual sizes on Hugging Face).

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

mradermacher/karakuri-midrose-CV-GGUF

Converted and published by a third party About this label

Last checked: Nov 11, 2026

Architecture
llama
Supported before llama.cpp b4409
Parameters
69.2B
Max context length
4,096
File size and memory per quantization for karakuri-midrose-CV (mradermacher/karakuri-midrose-CV-GGUF)
Quantization File size Measured Quality guide 4,096 max
Q2_K 25.6 GB Very large 27.6 GB
Q3_K_S 30.1 GB Large 32.0 GB
Q3_K_M 33.4 GB Medium 35.4 GB
Q3_K_L 36.3 GB Medium 38.3 GB
IQ4_XS 37.3 GB Small 39.3 GB
Q4_K_S 39.4 GB Medium 41.4 GB
Q4_K_M 41.6 GB Small 43.5 GB
Q5_K_S 47.6 GB Small 49.6 GB
Q5_K_M 48.9 GB Very small 50.9 GB 
Ollama  ollama run hf.co/mradermacher/karakuri-midrose-CV-GGUF:Q4_K_M
llama.cpp  llama-server -hf mradermacher/karakuri-midrose-CV-GGUF:Q4_K_M

How to run

Example commands using Q4_K_M. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/mradermacher/karakuri-midrose-CV-GGUF:Q4_K_M

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf mradermacher/karakuri-midrose-CV-GGUF:Q4_K_M

LM Studio

Paste mradermacher/karakuri-midrose-CV-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run karakuri-midrose-CV (Q4_K_M)?
The file size is 41.6 GB (measured). With a 4,096-token context, the estimated memory including the KV cache is 43.5 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
What is the command to run karakuri-midrose-CV with Ollama?
Run "ollama run hf.co/mradermacher/karakuri-midrose-CV-GGUF:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.