Esobold
EsoTest_GGUFs
- Parameters
- 30.7B
- Max context length
- 262,144
- Architecture
- gemma4
- llama.cpp
- b8637+
About EsoTest_GGUFs
EsoTest_GGUFs is a model published in GGUF format. GGUF files are published by Esobold/EsoTest_GGUFs. It has about 30.7B parameters, the gemma4 architecture, a maximum context length of 262,144 tokens (values written in the GGUF).
There are 5 quantizations, with file sizes from 9.53 GB (Q8_0) to 21.8 GB (Q5_K_M) (actual sizes on Hugging Face).
Running Q4_K_M (18.7 GB) with an 8,192-token context needs an estimated 21.7 GB of memory, and an estimated 23.7 GB at 32,768 tokens. For 8,192 tokens, a GPU with 24 GB or more of VRAM (such as GeForce RTX 3090 Ti, GeForce RTX 4090), or a Mac with 24 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom). The smallest, Q8_0 (9.53 GB), needs an estimated 12.5 GB at 8,192 tokens.
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
Last checked: Nov 11, 2026
- Architecture
- gemma4
- llama.cpp b8637 and later
- Parameters
- 30.7B
- Max context length
- 262,144
| Quantization | File size Measured | Quality guide | 4,096 | 8,192 | 16,384 | 32,768 | 65,536 | 131,072 | 262,144 max |
|---|---|---|---|---|---|---|---|---|---|
| Q8_0 MiMo-V2.6-Distill-Qwen-9B-S3half-r7-merged.Q8_0 | 9.53 GB | Nearly identical | 12.2 GB | 12.5 GB | 13.2 GB | 14.5 GB | 17.2 GB | 22.6 GB | 33.3 GB |
| Q8_0 MiMo-V2.6-Distill-Qwen-9B-S3half-r8-dpo-merged.Q8_0 | 9.53 GB | Nearly identical | 12.2 GB | 12.5 GB | 13.2 GB | 14.5 GB | 17.2 GB | 22.6 GB | 33.3 GB |
| Q8_0 MiMo-V2.6-Distill-Qwen-9B-S3half-r9-merged.Q8_0 | 9.53 GB | Nearly identical | 12.2 GB | 12.5 GB | 13.2 GB | 14.5 GB | 17.2 GB | 22.6 GB | 33.3 GB |
| IQ4_XS Tv1.IQ4_XS | 16.7 GB | Small | 19.4 GB | 19.7 GB | 20.4 GB | 21.8 GB | 24.4 GB | 29.8 GB | 40.5 GB |
| IQ4_XS g4_31b_recipe_Mx5.IQ4_XS | 16.7 GB | Small | 19.4 GB | 19.7 GB | 20.4 GB | 21.8 GB | 24.4 GB | 29.8 GB | 40.5 GB |
| IQ4_XS g4_31b_itdgutc_honDPO.IQ4_XS | 16.7 GB | Small | 19.4 GB | 19.7 GB | 20.4 GB | 21.8 GB | 24.4 GB | 29.8 GB | 40.5 GB |
| IQ4_XS g4_31b_itdgutc_s080.IQ4_XS | 16.7 GB | Small | 19.4 GB | 19.7 GB | 20.4 GB | 21.8 GB | 24.4 GB | 29.8 GB | 40.5 GB |
| Q4_K_S | 17.8 GB | Medium | 20.4 GB | 20.8 GB | 21.4 GB | 22.8 GB | 25.5 GB | 30.8 GB | 41.6 GB |
| Q4_K_M g4_31b_itmx5_fable_s080.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TwoEgypts.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-Woodcut.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TemperateParallel.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-SubtropicalPterodactyl.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-Mesopotamia.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-BeachBooth.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-ContinentOfMu.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-IsItNessie.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-HieronymusBosch.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Gemma4-Gutenberg-31B-Protestant.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-LandmarkNavigation.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-PrehistoricVolcano.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TijuanaBible.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TypoArcheopterix.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-RiverDelta.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-ThornSteppe.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TypoPterodactyl.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Gpb.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Mx5_Stack_A.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Tv3.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Mx5_Stack_B.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Mx5_StackB_10_30.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Mx5DS.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M stkb_10_30_v10.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Sv2.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Tv1.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M DSg030m.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Iv2_runpod.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_HBv1.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Iv3_runpod.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Jv2.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Jv4.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Jv4H10.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Lu4.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Lv4.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Mu2R.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Mx5.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_Mx5RPD.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_recipe_MxMel1.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M darkgem_gutc_s05.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_itdgutc_s080.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_itmx5_s080.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M darkgem_pwf_s05.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M darkgem_lowmask_s03.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M darkgem_DG_s05.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M darkgem_DG_s03.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gutenberg_mx5_masked_s06.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gut_mask_C_rank4.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M caveman_dgutc_rank4_s10.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M robinson-31b-Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M bengunn-31b-Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M GhostShip-31b-Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TemporarySecretary.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-HangTwelve.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-LandOfMu.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-SecretSprings.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-SpotToDig.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-SpringSauna.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-WaterfallCave.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TropicalParallel.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-TropicalPterodactyl.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-UofMiskatonic.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-VolcanicPterodactyl.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M g4_31b_moonrocks_eqx0001.Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-VitrificationOrder-Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M gemma-4-31b-MoonRocks-Q4_K_M | 18.7 GB | Small | 21.4 GB | 21.7 GB | 22.4 GB | 23.7 GB | 26.4 GB | 31.8 GB | 42.5 GB |
| Q4_K_M Mx5D_05.Q4_K_M | 19.5 GB | Small | 22.1 GB | 22.5 GB | 23.2 GB | 24.5 GB | 27.2 GB | 32.5 GB | 43.3 GB |
| Q4_K_M Mx5DS_05.Q4_K_M | 19.5 GB | Small | 22.1 GB | 22.5 GB | 23.2 GB | 24.5 GB | 27.2 GB | 32.5 GB | 43.3 GB |
| Q4_K_M Mx5_st_a050.Q4_K_M | 19.5 GB | Small | 22.1 GB | 22.5 GB | 23.2 GB | 24.5 GB | 27.2 GB | 32.5 GB | 43.3 GB |
| Q4_K_M gut_sthm_d09.Q4_K_M | 19.5 GB | Small | 22.1 GB | 22.5 GB | 23.2 GB | 24.5 GB | 27.2 GB | 32.5 GB | 43.3 GB |
| Q4_K_M gutenberg_mx5_st03.Q4_K_M | 19.5 GB | Small | 22.1 GB | 22.5 GB | 23.2 GB | 24.5 GB | 27.2 GB | 32.5 GB | 43.3 GB |
| Q4_K_M gemma-4-31b-nearswap-garnet-scotoma-Q4_K_M | 19.5 GB | Small | 22.1 GB | 22.5 GB | 23.2 GB | 24.5 GB | 27.2 GB | 32.5 GB | 43.3 GB |
| Q4_K_M darkgem_gutc_st_a050.Q4_K_M | 19.8 GB | Small | 22.5 GB | 22.8 GB | 23.5 GB | 24.9 GB | 27.5 GB | 32.9 GB | 43.6 GB |
| Q5_K_M g4_31b_itmx5_s080.Q5_K_M | 21.8 GB | Very small | 24.5 GB | 24.8 GB | 25.5 GB | 26.9 GB | 29.5 GB | 34.9 GB | 45.7 GB |
| Q5_K_M g4_31b_recipe_Mx5.Q5_K_M | 21.8 GB | Very small | 24.5 GB | 24.8 GB | 25.5 GB | 26.9 GB | 29.5 GB | 34.9 GB | 45.7 GB |
Ollama ollama run hf.co/Esobold/EsoTest_GGUFs:Q4_K_M
llama.cpp llama-server -hf Esobold/EsoTest_GGUFs:Q4_K_M
Generation speed on common GPUs and Macs (estimated)
A rough guide to how fast Q4_K_M (18.7 GB) generates text. Each token reads the model weights once, so the upper limit is memory bandwidth ÷ file size. The guide is 60–80% of that, where most published measurements fall.
| Device | Memory bandwidth | Guide (tokens/s) Estimated | Upper limit |
|---|---|---|---|
| GeForce RTX 3090 24 GB | 936 GB/s | 30–40 | 50 |
| GeForce RTX 4090 24 GB | 1,008 GB/s | 32–43 | 54 |
| GeForce RTX 5090 32 GB | 1,792 GB/s | 58–77 | 96 |
| Apple M4 32 GB | 120 GB/s | 3.9–5.1 | 6.4 |
| Apple M4 Pro 48 GB | 273 GB/s | 8.8–12 | 15 |
| Apple M5 Ultra 96 GB | 1,200 GB/s | 39–51 | 64 |
Estimates only. Prompt processing speed (limited by compute) is not included. Longer contexts and offloading part of the model to the CPU make it slower. Macs are shown only when installed memory is at least 4/3 of what is needed. Devices without published bandwidth (some GeForce cards, etc.) are not shown.
How to run
Mainline llama.cpp can load this model's format (gemma4) from b8637 (Apr 2, 2026) onward. Ollama and LM Studio bundle llama.cpp internally, so an older app fails to load it with errors such as "unknown model architecture". If that happens, update the app.
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/Esobold/EsoTest_GGUFs:Q4_K_M
llama.cpp
Pass the repository and quantization name to llama-server (or llama-cli) with -hf.
llama-server -hf Esobold/EsoTest_GGUFs:Q4_K_M
LM Studio
Paste Esobold/EsoTest_GGUFs into the search box, download it, and choose the quantization from the file list.
Models of a similar size (other developers)
-
27.3B
Qwen
Qwen3.8-27B
- UD-Q4_K_M size
- 16.5 GB
- Memory at 8K
- 18.2 GB
Measured Estimated VRAM 24 GB+
-
35.5B
huihui-ai
Huihui-Qwen3.6-35B-A3B-abliterated-MTP
- Q2_K size
- 13.2 GB
- Memory at 8K
- 14.5 GB
Measured Estimated VRAM 16 GB+
-
35.5B
ornith-ai
Ornith-1.5-35B-A3B
- Q4_K_M size
- 21.7 GB
- Memory at 8K
- 23.0 GB
Measured Estimated VRAM 24 GB+
-
27.3B
huihui-ai
Huihui-Qwen3.8-27B-abliterated
- Q4_K_M size
- 16.6 GB
- Memory at 8K
- 18.3 GB
Measured Estimated VRAM 24 GB+
-
25.2B
farbodtavakkoli
OTel-2.0-Decision-26B-A4B-4bit
- Q4_K_M size
- 16.8 GB
- Memory at 8K
- 18.4 GB
Measured Estimated VRAM 24 GB+
-
27.3B
JonathanColetti
Qwen3.8-27B-Uncensored
- Q4_K_M size
- 16.5 GB
- Memory at 8K
- 18.3 GB
Measured Estimated VRAM 24 GB+
Frequently asked questions
- How much memory do I need to run EsoTest_GGUFs (Q4_K_M)?
- The file size is 18.7 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 21.7 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
- Does EsoTest_GGUFs run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
- 8 GB: no quantization fits; 12 GB: up to Q8_0 (est. 12.5 GB); 16 GB: up to Q8_0 (est. 12.5 GB); 24 GB: up to Q5_K_M (est. 24.8 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
- What is the command to run EsoTest_GGUFs with Ollama?
- Run "ollama run hf.co/Esobold/EsoTest_GGUFs:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.