AMD · consumer

Radeon RX 6600

Radeon RX 6600 has 8 GB of VRAM at 224 GB/s — about 7.44 GiB usable after driver and compositor overhead. 1399 of 2118 indexed models fit at 4K context with f16 KV.

Spec sheet· bandwidth, theoreticalFrom the file· fit from summed bytesPredicted· speed
Memory
8 GB
GDDR6
Bandwidth
224 GB/s
128-bit bus
Tensor FP16
—
dense
TDP
132 W
$329 MSRP
Context4K8K16K32K64K128K
KV cachef16q8_0q4_0quantizing the KV cache is a ~2× lever on the dominant term at long context
text 1204vision language 101image 2video 7embedding 26audio tts 21audio asr 38

What fits at 4K context

largest quantization that fits, per model · 1399 of 2118 indexed
ModelBest quantParamsWeights●KV●Total in memory◐Headroom◐tok/s◐
Ling-liteMoEIQ2_M16.8B6.33 GiB0.22 GiB7.44 GiB0.00 GiB65±37%
Nexa-AI-4x4B-InstructMoEI1-Q3_K_L12.1B5.96 GiB0.56 GiB7.44 GiB0.00 GiB22±37%
Bonsai-8B-unpackedQ5_K_L8.2B5.94 GiB0.56 GiB7.43 GiB0.01 GiB22±26.5%
LFM2.5-Queen-Opus-4.7-8B-A1BMoEI1-Q6_K8.5B6.48 GiB0.05 GiB7.43 GiB0.01 GiB63±37%
LFM2.5-8B-A1B-KO-SFTMoEI1-Q6_K8.5B6.48 GiB0.05 GiB7.43 GiB0.01 GiB63±37%
LFM2.5-8B-A1B-hereticMoEI1-Q6_K8.5B6.48 GiB0.05 GiB7.43 GiB0.01 GiB63±37%
LFM2.5-8B-A1B-SOMPOA-heresyMoEI1-Q6_K8.5B6.48 GiB0.05 GiB7.43 GiB0.01 GiB63±37%
Huihui-LFM2.5-8B-A1B-abliteratedMoEI1-Q6_K8.5B6.48 GiB0.05 GiB7.43 GiB0.01 GiB63±37%
Supertron2.1-8B-A1BMoEI1-Q6_K8.5B6.48 GiB0.05 GiB7.43 GiB0.01 GiB63±37%
LFM2.5-8B-A1BMoEQ6_K8.5B6.48 GiB0.05 GiB7.43 GiB0.01 GiB63±37%
gemma-7bI1-Q4_K_S8.5B4.70 GiB1.75 GiB7.42 GiB0.02 GiB22±26.5%
Ministral-3-8B-Instruct-2512-BF16Q5_K_L8.9B5.95 GiB0.53 GiB7.42 GiB0.02 GiB22±26.5%
dolphin-2.9.2-Phi-3-MediumKV unresolvedIQ3_S14.0B5.68 GiB0.78 GiB7.42 GiB0.02 GiB22±26.5%
Cydonia-v1.3-Magnum-v4-22BI1-IQ2_XXS22.2B5.58 GiB0.88 GiB7.42 GiB0.02 GiB22±26.5%
Mistral-Small-22B-ArliAI-RPMax-v1.1I1-IQ2_XXS22.2B5.58 GiB0.88 GiB7.42 GiB0.02 GiB22±26.5%
magnum-v4-22bI1-IQ2_XXS22.2B5.58 GiB0.88 GiB7.42 GiB0.02 GiB22±26.5%
Mistral-Small-Instruct-2409IQ2_XXS22.2B5.58 GiB0.88 GiB7.42 GiB0.02 GiB22±26.5%
Codestral-22B-v0.1IQ2_XXS22.2B5.58 GiB0.88 GiB7.42 GiB0.02 GiB22±26.5%
Ministral-3-14B-Instruct-2512-BF16-abliteratedI1-IQ3_M13.9B5.84 GiB0.63 GiB7.42 GiB0.02 GiB22±26.5%
Ministral-3-14B-Instruct-2512-BF16IQ3_M13.9B5.84 GiB0.63 GiB7.42 GiB0.02 GiB22±26.5%
Ministral-3-14B-Reasoning-2512-UncensoredI1-IQ3_M13.9B5.84 GiB0.63 GiB7.42 GiB0.02 GiB22±26.5%
Wan2.1-T2V-1.3BQ4_01.4B6.50 GiB0.00 GiB7.42 GiB0.02 GiB22±26.5%
dolphin-2.9.1-mixtral-1x22bMoEI1-IQ2_XXS22.2B5.58 GiB0.88 GiB7.42 GiB0.02 GiB13±37%
Qwen3.6-35B-A3B-REAM-160-ru-agentMoEIQ2_XXS23.6B6.43 GiB0.08 GiB7.42 GiB0.02 GiB93±37%
codegeex4-all-9bIQ3_XXS9.4B3.97 GiB2.50 GiB7.41 GiB0.03 GiB22±26.5%
zeta-2Q5_K_L8.3B5.97 GiB0.50 GiB7.41 GiB0.03 GiB22±26.5%
glm-4-9b-chatIQ3_XXS9.4B3.97 GiB2.50 GiB7.41 GiB0.03 GiB22±26.5%
Gemma-4-12B-StyleTuneI1-IQ3_M13.0B5.74 GiB0.72 GiB7.41 GiB0.03 GiB22±26.5%
gemma-4-12b-heretic-styletune-headI1-IQ3_M12.0B5.74 GiB0.72 GiB7.41 GiB0.03 GiB22±26.5%
syrian-gemma-12bI1-IQ3_M13.0B5.74 GiB0.72 GiB7.41 GiB0.03 GiB22±26.5%
SambaLingo-Japanese-ChatI1-Q5_K_S6.9B4.48 GiB2.00 GiB7.40 GiB0.04 GiB22±26.5%
Ling-mini-2.0MoEIQ3_XS16.3B6.35 GiB0.16 GiB7.40 GiB0.04 GiB98±37%
UncensoredLM-DeepSeek-R1-Distill-Qwen-14BIQ3_XS14.2B5.73 GiB0.72 GiB7.40 GiB0.04 GiB22±26.5%
INTELLECT-1-InstructI1-Q4_K_M10.2B5.80 GiB0.66 GiB7.40 GiB0.04 GiB22±26.5%
Qwythos-9B-v2Q4_K_L9.7B6.34 GiB0.13 GiB7.40 GiB0.04 GiB22±26.5%
Tess-4-9BQ4_K_L9.7B6.34 GiB0.13 GiB7.40 GiB0.04 GiB22±26.5%
Qwen3.5-9B-BaseQ5_19.7B6.33 GiB0.13 GiB7.39 GiB0.05 GiB22±26.5%
v6-Finch-7B-HFQ4_07.6B4.45 GiB2.00 GiB7.39 GiB0.05 GiB22±26.5%
rwkv-6-world-7bQ4_07.6B4.45 GiB2.00 GiB7.39 GiB0.05 GiB22±26.5%
Teuken-7B-instruct-research-v0.4Q6_K_L7.5B6.33 GiB0.13 GiB7.39 GiB0.05 GiB22±26.5%
internlm2-math-plus-20bI1-IQ2_XS19.9B5.68 GiB0.75 GiB7.39 GiB0.05 GiB22±26.5%
LocateAnything-3BBF163.8B6.34 GiB0.14 GiB7.39 GiB0.05 GiB22±26.5%
deepseek-math-7b-instructQ5_K_M6.9B4.59 GiB1.88 GiB7.39 GiB0.05 GiB22±26.5%
deepseek-llm-7b-chatQ5_K_M6.9B4.59 GiB1.88 GiB7.39 GiB0.05 GiB22±26.5%
Janus-Pro-7BI1-Q5_K_M7.4B4.59 GiB1.88 GiB7.39 GiB0.05 GiB22±26.5%
deepseek-coder-7b-instruct-v1.5I1-Q5_K_M6.9B4.59 GiB1.88 GiB7.39 GiB0.05 GiB22±26.5%
Phi-3-medium-128k-instructQ3_K_S14.0B5.65 GiB0.78 GiB7.39 GiB0.05 GiB22±26.5%
Phi-3-medium-4k-instructI1-IQ3_S14.0B5.65 GiB0.78 GiB7.39 GiB0.05 GiB22±26.5%
Qwen2.5-3B-Instruct-abliteratedF163.1B6.33 GiB0.14 GiB7.39 GiB0.05 GiB22±26.5%
GRM-Kerlin-3bF163.4B6.33 GiB0.14 GiB7.39 GiB0.05 GiB22±26.5%
Nous-Hermes-2-SOLAR-10.7BQ4_K_S10.7B5.70 GiB0.75 GiB7.39 GiB0.05 GiB22±26.5%
SOLAR-10.7B-Instruct-v1.0I1-Q4_K_S10.7B5.70 GiB0.75 GiB7.39 GiB0.05 GiB22±26.5%
Garnet-OCR-3B-0422F164.1B6.33 GiB0.14 GiB7.38 GiB0.06 GiB22±26.5%
Rocinante-XL-16B-v1IQ2_S16.1B5.59 GiB0.84 GiB7.38 GiB0.06 GiB22±26.5%
granite-4.1-8bQ5_K_M8.8B5.82 GiB0.63 GiB7.38 GiB0.06 GiB22±26.5%
deepseek-coder-6.7b-instructQ5_K_M6.7B4.46 GiB2.00 GiB7.38 GiB0.06 GiB22±26.5%
deepseek-coder-6.7b-baseQ5_K_M6.7B4.46 GiB2.00 GiB7.38 GiB0.06 GiB22±26.5%
deepseek-coder-6.7B-kexerI1-Q5_K_M6.7B4.46 GiB2.00 GiB7.38 GiB0.06 GiB22±26.5%
Magicoder-S-DS-6.7BI1-Q5_K_M6.7B4.46 GiB2.00 GiB7.38 GiB0.06 GiB22±26.5%
MathCoder2-CodeLlama-7BQ5_K_M6.7B4.45 GiB2.00 GiB7.38 GiB0.06 GiB22±26.5%
●From the file◐Predictedwhat these mean

Speed is modeled, not measured: decode is memory-bandwidth bound, so tokens per second is bytes read per token against achievable bandwidth. Mixture-of-experts models carry a wider band because only the routed experts are read each step, and few have been measured publicly.

Measured on this card

third-party benchmarks, aggregated
Workload◍MedianMiddle 50%Runs
Image generation2.06 it/s0.90–3.3091
Benchmarked· n=91

Aggregated from community-submitted runs, so the spread is wide by nature — it covers different models, resolutions, step counts and settings, not one controlled configuration. Read the middle 50% rather than the median alone. These figures are reproduced with attribution from vladmandic-sd-data-benchmark, which publishes no licence — so we display and link rather than redistribute them.

Questions people ask

What AI models can a Radeon RX 6600 run?
1399 of 2118 indexed open-weight models fit a Radeon RX 6600 at 4,096 context with f16 KV cache, the largest being Ling-lite at IQ2_M. That covers text, vision-language, image, video and speech models.
How much usable memory does a Radeon RX 6600 actually have?
Its nameplate is 8 GB, but about 7.44 GiB is available to a model once driver and compositor overhead is accounted for.
Is a Radeon RX 6600 fast for local AI?
Its memory bandwidth is 224 GB/s, and that figure — not teraflops — is what governs token generation speed. Capacity decides what you can run; bandwidth decides how fast it runs.